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

    Neuronpedia

    INDEX
    Explanations

    the number 140

    oai_token-act-pair · gpt-3.5-turbo

    references to character limits or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gart
    -0.74
    gotten
    -0.71
    yer
    -0.70
    ding
    -0.69
    rics
    -0.69
    holder
    -0.69
    tail
    -0.68
    estine
    -0.68
    frey
    -0.68
    tails
    -0.67
    POSITIVE LOGITS
     ILCS
    0.86
    xual
    0.84
     chars
    0.81
    mph
    0.78
    993
    0.74
    CRIP
    0.73
    lbs
    0.73
     lbs
    0.71
    ologist
    0.67
    XM
    0.66
    Act Density 0.027%

    No Known Activations