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

    Neuronpedia

    INDEX
    Explanations

    descriptions of emotions or responses related to past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AttributeSet
    -0.85
    gypti
    -0.81
     /\.(
    -0.74
     Ameri
    -0.71
     Accra
    -0.69
     PCC
    -0.68
     Ladybug
    -0.68
     häls
    -0.67
     LAC
    -0.67
     DPI
    -0.66
    POSITIVE LOGITS
     Was
    0.93
    Was
    0.86
     was
    0.84
    Wasn
    0.80
    was
    0.79
     wasn
    0.74
     وكان
    0.72
     Initially
    0.72
     WAS
    0.69
    Initially
    0.69
    Act Density 0.335%

    No Known Activations