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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical processes, particularly related to methods and code implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.59
    clav
    -0.46
    Portail
    -0.43
    こともあります
    -0.43
    encodeWith
    -0.43
    Abitanti
    -0.42
    背
    -0.42
     же
    -0.42
    SL
    -0.41
    FormState
    -0.40
    POSITIVE LOGITS
    +#+#
    0.85
    instead
    0.77
    dafx
    0.75
     instead
    0.75
     вместо
    0.70
     Statt
    0.70
     Instead
    0.69
     zamiast
    0.68
     '\\;'
    0.66
    Instead
    0.60
    Act Density 0.831%

    No Known Activations