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

    Neuronpedia

    INDEX
    Explanations

    mentions of a significant distance or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of ongoing process or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cca
    -0.67
    vec
    -0.63
     murd
    -0.60
    driving
    -0.59
    NetMessage
    -0.58
    uras
    -0.58
    rium
    -0.55
    ums
    -0.55
    bec
    -0.55
    pron
    -0.55
    POSITIVE LOGITS
     nobody
    0.89
     none
    0.88
     hasn
    0.82
     unsuccessful
    0.82
     haven
    0.74
     there
    0.74
     nothing
    0.74
     indications
    0.73
     neither
    0.70
     only
    0.69
    Act Density 0.043%

    No Known Activations