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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to community and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨاÙĨ
    -0.15
    setting
    -0.15
    HEL
    -0.15
    374
    -0.14
    oven
    -0.14
    este
    -0.14
    udit
    -0.14
     Gins
    -0.14
    scape
    -0.14
    anya
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥ«
    0.17
    irket
    0.17
    zl
    0.15
    ohl
    0.14
    undler
    0.14
    IGO
    0.14
    .ajax
    0.13
    edl
    0.13
    ;left
    0.13
    opsis
    0.13
    Act Density 0.275%

    No Known Activations