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

    Neuronpedia

    INDEX
    Explanations

    instances of deception or pretense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /fw
    -0.16
    _orient
    -0.16
     comps
    -0.15
    ãģĦãĤĭ
    -0.15
    .DAL
    -0.15
    usercontent
    -0.14
     ç±
    -0.14
    oggle
    -0.14
    atron
    -0.14
    hang
    -0.14
    POSITIVE LOGITS
    usto
    0.17
    ÅĤu
    0.15
     McCl
    0.15
    ugeot
    0.15
    sten
    0.15
    annah
    0.15
    ouri
    0.14
     Gap
    0.14
    inston
    0.14
     Gest
    0.14
    Act Density 0.041%

    No Known Activations