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

    Neuronpedia

    INDEX
    Explanations

    words related to blindness or the concept of being unable to see

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nbsp
    -0.16
    STS
    -0.15
     abre
    -0.15
    zzo
    -0.15
    TRA
    -0.14
    ters
    -0.14
    beiter
    -0.14
    ÅĻe
    -0.14
     breeds
    -0.14
    OfDay
    -0.14
    POSITIVE LOGITS
    fold
    0.29
    phem
    0.25
    eting
    0.25
    ishments
    0.23
    eted
    0.21
    spot
    0.19
    ly
    0.19
    side
    0.18
    enstein
    0.18
    ishment
    0.18
    Act Density 0.055%

    No Known Activations