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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic papers or publications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.81
    SourceFile
    -0.78
    TY
    -0.74
    ãĥ¯ãĥ³
    -0.71
    externalActionCode
    -0.70
    waters
    -0.70
    ENCY
    -0.68
    DERR
    -0.68
    ptives
    -0.66
    Fans
    -0.65
    POSITIVE LOGITS
     behalf
    1.48
    erous
    1.04
    yx
    0.89
     topics
    0.88
    site
    0.86
    shore
    0.83
    eday
    0.82
    eworld
    0.78
     steroids
    0.78
     Mondays
    0.77
    Act Density 0.182%

    No Known Activations