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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or spaces indicating separation or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences of repeated underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.95
     Magal
    -0.94
    InvalidProtocol
    -0.90
    piecz
    -0.89
    erequisites
    -0.86
     Stav
    -0.85
    vábbi
    -0.85
    brainly
    -0.83
    ApiProperty
    -0.82
     Albrecht
    -0.82
    POSITIVE LOGITS
             
    1.23
     Ronde
    0.88
    0.84
     Mier
    0.81
     LOGGER
    0.80
    🤣🤣
    0.80
     Mors
    0.77
     coraggio
    0.76
    Hoy
    0.76
     Siro
    0.75
    Act Density 0.058%

    No Known Activations