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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.01
    ÄŁ
    -0.77
    LER
    -0.77
    REG
    -0.76
    BIL
    -0.74
    vier
    -0.73
    tower
    -0.73
    ammers
    -0.71
    noon
    -0.71
    SHIP
    -0.70
    POSITIVE LOGITS
    ised
    1.18
    ization
    1.05
    ities
    1.04
    ized
    1.04
    isation
    1.00
     vend
    0.98
     belongings
    0.95
    izations
    0.94
    isations
    0.93
     feelings
    0.93
    Act Density 0.018%

    No Known Activations