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

    Neuronpedia

    INDEX
    Explanations

    personal information and stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.03
    FIL
    -0.76
    REG
    -0.76
    UMP
    -0.74
    LER
    -0.72
    å¾
    -0.71
    vous
    -0.68
    LOS
    -0.67
    DAY
    -0.66
     GOODMAN
    -0.66
    POSITIVE LOGITS
    ised
    1.14
    ities
    1.09
    ized
    1.07
    izations
    1.04
    ization
    1.03
    isations
    1.02
    izing
    0.97
    isation
    0.96
     belongings
    0.95
    istic
    0.94
    Act Density 1.230%

    No Known Activations