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

    Neuronpedia

    INDEX
    Explanations

    strings of characters and numbers that may represent technical information like codes or identifiers

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.94
    iets
    -0.86
     inflamm
    -0.77
    HCR
    -0.74
    lik
    -0.74
    xual
    -0.73
    WAYS
    -0.73
     payoff
    -0.73
    LESS
    -0.72
    mort
    -0.70
    POSITIVE LOGITS
    fe
    0.88
    cf
    0.85
    fd
    0.82
    fc
    0.80
    9
    0.78
    da
    0.77
    ffe
    0.75
    cd
    0.74
    7
    0.74
    df
    0.72
    Act Density 0.082%

    No Known Activations