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

    Neuronpedia

    INDEX
    Explanations

    references to actions or activities being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ock
    -0.18
    ogn
    -0.17
    kos
    -0.16
    avin
    -0.15
    æ¦
    -0.15
    ALSE
    -0.14
    neider
    -0.14
    ket
    -0.14
    lop
    -0.13
     DeV
    -0.13
    POSITIVE LOGITS
     justice
    0.17
    plus
    0.15
     mistakes
    0.14
    heimer
    0.14
    .getElements
    0.14
    206
    0.14
    åĺī
    0.14
     Tos
    0.13
     mistake
    0.13
    zens
    0.13
    Act Density 0.068%

    No Known Activations