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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equal distribution or balance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distribution and balance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.84
    OLOG
    -0.79
    ger
    -0.78
    gers
    -0.77
    ourke
    -0.76
    artifacts
    -0.74
     Gest
    -0.73
    anamo
    -0.70
    oggles
    -0.68
     firsthand
    -0.67
    POSITIVE LOGITS
     spaced
    0.98
     evenly
    0.97
     distribute
    0.96
    sheets
    0.90
     ILCS
    0.89
     divided
    0.88
     distributed
    0.88
    sheet
    0.87
    soType
    0.85
     disperse
    0.84
    Act Density 0.026%

    No Known Activations