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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to different fields such as finance, medicine, and law

    oai_token-act-pair · gpt-3.5-turbo

    empty or null content in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.75
    acebook
    -0.62
    mble
    -0.61
    milo
    -0.61
     destro
    -0.57
    emale
    -0.57
    pherd
    -0.56
    herer
    -0.56
    atever
    -0.55
     Niet
    -0.53
    POSITIVE LOGITS
     warfare
    0.53
     caps
    0.51
     diplomacy
    0.51
    ÂŃ
    0.51
    otin
    0.50
    bugs
    0.50
     proportions
    0.49
     accidents
    0.49
    âĢIJ
    0.49
    Semitism
    0.49
    Act Density 0.744%

    No Known Activations