Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific terminology and concepts related to housing and architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.43
    2:0.02
    3:0.02
    4:0.02
    5:0.22
    6:0.02
    7:0.01
    8:0.02
    9:0.05
    10:0.03
    11:0.01
    Negative Logits
    uti
    -1.84
    uto
    -1.73
    idel
    -1.70
     sqor
    -1.61
    aimon
    -1.59
    oss
    -1.56
    ills
    -1.55
    emis
    -1.53
     Removed
    -1.48
    gmail
    -1.46
    POSITIVE LOGITS
    -
    2.82
    -"
    2.32
    _>
    2.20
    -$
    2.19
    ‑
    2.19
    -'
    2.12
    ْ
    2.05
    -)
    1.99
    -|
    1.92
    -.
    1.91
    Act Density 0.097%

    No Known Activations