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

    Neuronpedia

    INDEX
    Explanations

    references to magical abilities or spells related to offensive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.47
    SourceChecksum
    -0.46
    hata
    -0.45
    ci
    -0.44
     ville
    -0.44
     ta
    -0.43
    ®
    -0.43
     Rubin
    -0.42
    fal
    -0.41
     Laden
    -0.41
    POSITIVE LOGITS
    +:+
    0.85
     pleaſure
    0.72
    LEncoder
    0.72
    SequentialGroup
    0.70
     cooldown
    0.68
     itſelf
    0.67
     StringTokenizer
    0.67
    Datuak
    0.66
    WAUKEE
    0.65
     oprot
    0.64
    Act Density 0.273%

    No Known Activations