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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns that follow a specific sequence

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers and their associated quantities, likely referring to scores, statistics, or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -1.02
    SPONSORED
    -0.95
    ··
    -0.78
    POST
    -0.77
    thinkable
    -0.74
    usted
    -0.73
    inement
    -0.73
    advertising
    -0.73
    ãĥ¼ãĤ¯
    -0.72
    adjusted
    -0.72
    POSITIVE LOGITS
     Ibid
    0.97
     Ort
    0.95
     Tel
    0.92
     Am
    0.91
     Nat
    0.90
     Nath
    0.90
     Lys
    0.89
     Ang
    0.88
     Ben
    0.87
     Lack
    0.87
    Act Density 0.129%

    No Known Activations