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

    Neuronpedia

    INDEX
    Explanations

    names of professions or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or individuals involved in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prev
    -0.75
     Encyclopedia
    -0.71
    eret
    -0.69
    Appearances
    -0.66
     Anyway
    -0.65
     Sakuya
    -0.65
     Kills
    -0.64
    incarn
    -0.64
     Omn
    -0.63
    resents
    -0.63
    POSITIVE LOGITS
     worried
    1.42
     clam
    1.39
     anx
    1.34
     worry
    1.27
     fear
    1.22
     fearing
    1.20
     rallied
    1.20
     protested
    1.18
     wondered
    1.18
     feared
    1.16
    Act Density 0.353%

    No Known Activations