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

    Neuronpedia

    INDEX
    Explanations

    phrases related to app features and membership criteria for services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    جوايز
    -0.61
     Италијани
    -0.55
    adpleegd
    -0.54
     ModelExpression
    -0.51
     suprême
    -0.50
     lisboa
    -0.49
     doppia
    -0.49
    WriteBarrier
    -0.49
    jà
    -0.48
    gga
    -0.47
    POSITIVE LOGITS
     small
    1.64
     smaller
    1.48
    small
    1.46
    Small
    1.36
     Small
    1.34
     SMALL
    1.32
    smaller
    1.31
    Smaller
    1.29
     Smaller
    1.25
    SMALL
    1.24
    Act Density 0.340%

    No Known Activations