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

    Neuronpedia

    INDEX
    Explanations

    words related to controversy or negative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.69
    __((
    -0.60
    ed
    -0.57
    closePath
    -0.53
    ️
    -0.52
    whole
    -0.52
    izations
    -0.51
    CWE
    -0.51
     sanguí
    -0.51
    eel
    -0.50
    POSITIVE LOGITS
    der
    0.95
    dle
    0.93
    die
    0.86
    ded
    0.86
    dies
    0.85
    ding
    0.83
    ders
    0.82
    dy
    0.82
    dles
    0.70
    dington
    0.69
    Act Density 0.366%

    No Known Activations