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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers with hyphens

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.74
    Interested
    -0.73
     Clicker
    -0.68
    Enough
    -0.67
    女
    -0.62
    emetery
    -0.62
     conduc
    -0.62
    Tags
    -0.60
    theless
    -0.60
    gently
    -0.59
    POSITIVE LOGITS
    fc
    0.71
    gery
    0.63
    fe
    0.63
     digest
    0.63
    aced
    0.61
    cf
    0.61
     ministerial
    0.59
    f
    0.59
    342
    0.58
    adem
    0.58
    Act Density 0.066%

    No Known Activations