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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and a theme of apathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieri
    -0.72
    amins
    -0.71
     skelet
    -0.70
    nikov
    -0.69
    Assembly
    -0.65
    ARM
    -0.65
    oter
    -0.65
     Citiz
    -0.64
    assic
    -0.63
     synagogue
    -0.63
    POSITIVE LOGITS
    ysis
    0.79
    hammad
    0.76
     actionGroup
    0.75
    Pg
    0.72
    fw
    0.69
    vt
    0.69
    milo
    0.66
    ei
    0.66
    fp
    0.66
    cules
    0.65
    Act Density 0.031%

    No Known Activations