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

    Neuronpedia

    INDEX
    Explanations

    percentages indicating significant data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lej
    -0.18
    aza
    -0.16
    lesia
    -0.16
    anzi
    -0.15
    za
    -0.15
    azzi
    -0.15
    _iff
    -0.14
     Ultra
    -0.14
     Forms
    -0.14
     Ring
    -0.14
    POSITIVE LOGITS
     Herbert
    0.14
    isman
    0.14
    ursal
    0.14
    Mag
    0.14
    shelf
    0.14
     dream
    0.14
    icer
    0.13
    okud
    0.13
     handleMessage
    0.13
     éģ
    0.13
    Act Density 0.060%

    No Known Activations