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

    Neuronpedia

    INDEX
    Explanations

    the presence of the '#' symbol, which typically indicates hashtags or identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.85
     صوتيه
    -0.85
     purpoſe
    -0.81
     pleaſure
    -0.80
    Personensuche
    -0.79
     Majefty
    -0.79
     greateſt
    -0.77
     reaſon
    -0.75
     fubject
    -0.74
     Jefus
    -0.73
    POSITIVE LOGITS
    rungsseite
    0.56
    IBarButtonItem
    0.47
    amazonaws
    0.44
    kwds
    0.44
    cfm
    0.43
    ducted
    0.42
    toh
    0.42
    ukk
    0.42
    Hrsg
    0.42
    Synth
    0.42
    Act Density 0.002%

    No Known Activations