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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unexpected or undesired situations in which individuals or groups find themselves

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal experiences and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.80
     Mub
    -0.77
    imize
    -0.69
    pour
    -0.67
    vert
    -0.67
    ritz
    -0.67
    oslov
    -0.65
    cemic
    -0.65
    grade
    -0.65
     Mehran
    -0.63
    POSITIVE LOGITS
    selves
    0.78
     tremend
    0.74
    peria
    0.73
     anew
    0.71
    CHAT
    0.71
    æ³
    0.68
     personally
    0.68
     wanting
    0.66
    ANS
    0.65
     creatively
    0.65
    Act Density 0.041%

    No Known Activations