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

    Neuronpedia

    INDEX
    Explanations

    entities or titles identified by the symbol "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    discrete numerical data and references to specific entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veter
    -0.74
     hiber
    -0.67
     dating
    -0.67
     allied
    -0.64
     capit
    -0.63
     shoulders
    -0.63
     imperson
    -0.63
     volunt
    -0.61
     wrists
    -0.61
     chairs
    -0.61
    POSITIVE LOGITS
    Imagine
    0.82
    ILLE
    0.82
    ³³³³³³³³³³³³³³³³
    0.82
    Photo
    0.81
    Express
    0.80
    verett
    0.79
    ³³³³
    0.77
    GREEN
    0.77
    ³³³
    0.76
    photo
    0.76
    Act Density 0.203%

    No Known Activations