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

    Neuronpedia

    INDEX
    Explanations

    negation phrases and words indicating absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stevenson
    -0.15
    quet
    -0.14
     Kidd
    -0.14
    oj
    -0.14
    .asp
    -0.14
    UNIT
    -0.13
    odox
    -0.13
    FORMANCE
    -0.12
    pak
    -0.12
    rypton
    -0.12
    POSITIVE LOGITS
    .scalablytyped
    0.18
    Extern
    0.15
    nite
    0.14
    .gdx
    0.14
    Ùĩر
    0.13
    TEMPL
    0.13
    efe
    0.13
    adora
    0.13
     Yunan
    0.13
    assin
    0.12
    Act Density 0.188%

    No Known Activations