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

    Neuronpedia

    INDEX
    Explanations

    words related to personal judgment or discretion

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal autonomy and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayn
    -0.65
    Sov
    -0.59
     referen
    -0.57
    ILA
    -0.55
    MSN
    -0.54
    yah
    -0.54
    mbuds
    -0.53
     corrid
    -0.53
    Ther
    -0.52
    MAP
    -0.52
    POSITIVE LOGITS
     ;)
    0.89
     persuasion
    0.87
     :)
    0.79
    !.
    0.78
     imaginable
    0.78
    _.
    0.76
    drive
    0.73
     :-)
    0.72
    *.
    0.72
    .<
    0.70
    Act Density 0.442%

    No Known Activations