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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political actions and discussions

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numerical values or quantities associated with events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favourite
    -0.68
     endeavour
    -0.68
     civilisation
    -0.66
     favoured
    -0.66
     honoured
    -0.66
    bourg
    -0.64
     Isis
    -0.63
     inactive
    -0.62
     equivalents
    -0.60
     organised
    -0.60
    POSITIVE LOGITS
    âĢ
    1.35
    âĺ
    1.25
    âĹı
    1.24
    ̶
    1.23
    ³³³³
    1.20
    ³³³³³³³³
    1.18
    ãĢ
    1.15
    ³³³
    1.12
    */
    1.12
    îĢ
    1.10
    Act Density 0.425%

    No Known Activations