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

    Neuronpedia

    INDEX
    Explanations

    ways things are presented or formatted

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate types or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivas
    -0.81
    isf
    -0.78
    owe
    -0.77
    ask
    -0.76
    Bridge
    -0.71
    NRS
    -0.70
    .–
    -0.69
    falls
    -0.68
    CHA
    -0.68
    ilver
    -0.67
    POSITIVE LOGITS
     Finder
    0.76
     Pope
    0.67
    Pope
    0.67
     Foss
    0.65
     Prayer
    0.65
     Suarez
    0.65
     aiding
    0.64
     Rudolph
    0.64
     Hurricane
    0.63
     facilitating
    0.63
    Act Density 0.089%

    No Known Activations