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

    Neuronpedia

    INDEX
    Explanations

    statements that express opinions or subjective views

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.99
     Chriftian
    -0.78
     Houſe
    -0.77
    ſelf
    -0.76
     himſelf
    -0.76
     ſtate
    -0.75
     houſe
    -0.71
     raiſ
    -0.71
    Atentamente
    -0.70
     myſelf
    -0.70
    POSITIVE LOGITS
     wasn
    0.71
     It
    0.70
     seems
    0.64
    The
    0.63
    It
    0.62
     kind
    0.61
     happened
    0.60
     متعلقه
    0.60
    playSound
    0.60
     The
    0.60
    Act Density 0.162%

    No Known Activations