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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or groups associated with conflict or geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    names and identifiers associated with individuals and groups in conflict or military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     builders
    -0.66
     glim
    -0.64
     manufact
    -0.64
     crochet
    -0.63
     xp
    -0.63
    isms
    -0.61
     Tinker
    -0.61
    poke
    -0.60
    conserv
    -0.60
    Engineers
    -0.60
    POSITIVE LOGITS
    azeera
    0.94
    awi
    0.94
    aghd
    0.92
    abi
    0.92
    ouf
    0.86
    aeda
    0.84
    aba
    0.82
    bia
    0.81
    andi
    0.78
    qqa
    0.76
    Act Density 0.056%

    No Known Activations