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

    Neuronpedia

    INDEX
    Explanations

    phrases where the expression "in all" is used

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or concepts in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anova
    -0.76
     Rouge
    -0.71
    IDS
    -0.70
    idable
    -0.68
    lash
    -0.67
    ube
    -0.67
    tis
    -0.66
    nect
    -0.64
    namese
    -0.64
    ãĥİ
    -0.62
    POSITIVE LOGITS
    ocating
    1.06
    igator
    0.97
    igators
    0.94
     manner
    0.92
    uding
    0.88
     kinds
    0.85
    iance
    0.85
    iances
    0.84
     sorts
    0.79
    usion
    0.79
    Act Density 0.042%

    No Known Activations