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

    Neuronpedia

    INDEX
    Explanations

    specific names (e.g., places, characters, films) and acronyms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambers
    -0.73
    ,,,,
    -0.72
    respective
    -0.71
     lax
    -0.70
    agher
    -0.69
    jad
    -0.67
    efully
    -0.66
    ourgeois
    -0.65
     privile
    -0.64
    perm
    -0.64
    POSITIVE LOGITS
     Lies
    1.09
     Darkness
    1.04
     Champions
    0.97
     Tomorrow
    0.95
     Thrones
    0.93
     Decay
    0.92
     Plenty
    0.92
     Nations
    0.90
     Wonders
    0.90
     Rage
    0.90
    Act Density 0.063%

    No Known Activations