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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific places or events

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated clauses or phrases within a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.57
    Unt
    -0.55
    estones
    -0.53
    minster
    -0.52
    role
    -0.51
    iku
    -0.49
    FW
    -0.49
    Bride
    -0.48
    ãĥ¥
    -0.48
    hedral
    -0.47
    POSITIVE LOGITS
     including
    0.74
     namely
    0.70
     please
    0.67
     albeit
    0.66
     however
    0.65
     huh
    0.64
     meanwhile
    0.63
     partName
    0.63
     which
    0.62
     provoking
    0.58
    Act Density 0.324%

    No Known Activations