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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or reflection in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )':
    -0.82
    )":
    -0.79
    ;';
    -0.71
    )*/
    -0.68
    )”.
    -0.67
    ).”
    -0.66
    )";
    -0.65
    )”
    -0.65
    ')],
    -0.64
    ).</
    -0.63
    POSITIVE LOGITS
    Jeez
    0.94
     goddamn
    0.90
    Fucking
    0.89
    principalTable
    0.88
    Worse
    0.85
    QMetaType
    0.84
     cherchés
    0.83
     fuckin
    0.82
     Damn
    0.80
    Damn
    0.80
    Act Density 0.789%

    No Known Activations