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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is speaking or expressing their opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences including dialogue and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vable
    -0.77
    ords
    -0.76
    rica
    -0.74
    rawdownloadcloneembedreportprint
    -0.70
    iffe
    -0.69
     Flavoring
    -0.67
    tnc
    -0.67
    APTER
    -0.65
    imore
    -0.64
    20439
    -0.64
    POSITIVE LOGITS
     hey
    1.32
     '
    1.27
     '[
    1.26
     `
    1.25
     "'
    1.23
     oh
    1.11
     "
    1.08
     wow
    1.08
     Hey
    1.06
     '(
    1.05
    Act Density 0.082%

    No Known Activations