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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authorization or approval

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory interjections or expressions of surprise and excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unwanted
    -0.75
     controvers
    -0.75
     convenience
    -0.73
     incorpor
    -0.73
     overloaded
    -0.72
    ktop
    -0.72
    inent
    -0.72
     inactive
    -0.72
     associ
    -0.71
     behavi
    -0.70
    POSITIVE LOGITS
    ï¸ı
    1.06
    ¯
    0.95
    °
    0.87
    âĶĢâĶĢâĶĢâĶĢ
    0.86
    âĶģ
    0.86
    âĻ¦
    0.86
    laughs
    0.83
    âĻ
    0.81
    ef
    0.81
    ~
    0.81
    Act Density 0.236%

    No Known Activations