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

    Neuronpedia

    INDEX
    Explanations

    exclamation points and phrases that indicate surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.65
    HSSF
    -0.57
    ötzlich
    -0.56
     nawr
    -0.55
    ocities
    -0.54
    chmal
    -0.52
    Obrigada
    -0.51
    様々
    -0.51
    getItemId
    -0.50
     član
    -0.50
    POSITIVE LOGITS
     Overall
    0.79
    Overall
    0.78
     Speaking
    0.77
     expect
    0.75
     unlike
    0.72
     overall
    0.72
     Expect
    0.70
     Compared
    0.69
     compared
    0.68
    Dislikes
    0.67
    Act Density 0.120%

    No Known Activations