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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and locations related to a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.98
    ~~~~
    -0.90
    inventoryQuantity
    -0.77
    20439
    -0.76
    USE
    -0.69
    ··
    -0.67
     Helpful
    -0.66
    TEXTURE
    -0.66
    REDACTED
    -0.65
    LEASE
    -0.65
    POSITIVE LOGITS
    inav
    0.93
    onite
    0.85
    bones
    0.83
    lege
    0.82
    ogram
    0.81
    ograms
    0.79
    arus
    0.78
    omed
    0.78
    omorphic
    0.77
     Seym
    0.76
    Act Density 0.028%

    No Known Activations