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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to competitions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names or terms related to characters or entities in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.78
    growth
    -0.71
    hemat
    -0.71
    ritic
    -0.68
    Downloadha
    -0.65
    PROV
    -0.64
     shr
    -0.63
    apple
    -0.62
    ãģķ
    -0.60
    Scotland
    -0.58
    POSITIVE LOGITS
    uel
    1.31
    theless
    1.07
    oaded
    0.85
    onge
    0.83
    ength
    0.82
     destro
    0.80
    inations
    0.79
    inus
    0.78
    iel
    0.77
    ocity
    0.77
    Act Density 0.004%

    No Known Activations