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

    Neuronpedia

    INDEX
    Explanations

    references to the term "world" and its descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illa
    -0.18
    ischen
    -0.17
    chen
    -0.16
    elor
    -0.16
     hoch
    -0.15
    ager
    -0.15
    .yy
    -0.14
    ardin
    -0.14
    orie
    -0.14
    variants
    -0.14
    POSITIVE LOGITS
     wide
    0.30
    -wide
    0.29
    Wide
    0.29
    wide
    0.28
     Wide
    0.28
    wid
    0.23
    -ren
    0.22
    -class
    0.19
     premiere
    0.19
     traveler
    0.18
    Act Density 0.039%

    No Known Activations