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

    Neuronpedia

    INDEX
    Explanations

    instances of deception or falsehood in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.73
    .
    -0.69
    ↵↵
    -0.65
    ↵
    -0.63
    !
    -0.62
    5
    -0.62
     (
    -0.57
    ?
    -0.56
     olsun
    -0.56
    3
    -0.56
    POSITIVE LOGITS
    eſ
    0.91
    YourGuide
    0.90
    ſſer
    0.89
     getF
    0.86
    ]='\
    0.85
    uests
    0.85
    ghijklmnop
    0.84
    IBLIO
    0.84
    arangay
    0.84
    itsubishi
    0.84
    Act Density 1.017%

    No Known Activations