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

    Neuronpedia

    INDEX
    Explanations

    formal or technical language that indicates complexity or specificity in a subject matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erule
    -0.15
    hiba
    -0.15
    -wsj
    -0.15
     Mood
    -0.15
    ulis
    -0.15
    afari
    -0.14
    ko
    -0.14
    riot
    -0.14
    314
    -0.14
    arak
    -0.13
    POSITIVE LOGITS
    endi
    0.15
     sóc
    0.15
    ottom
    0.14
     tagged
    0.14
     rem
    0.14
    .sorted
    0.14
     hic
    0.14
     provid
    0.14
     Esper
    0.14
    .scalablytyped
    0.13
    Act Density 0.016%

    No Known Activations