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

    Neuronpedia

    INDEX
    Explanations

    numeric and alphanumeric sequences, indicating a focus on codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andon
    -0.16
    Ī
    -0.15
    iesel
    -0.15
    erus
    -0.14
    estate
    -0.14
     ëĭ¤ìļ´
    -0.14
    oard
    -0.14
    legen
    -0.14
    ableObject
    -0.13
    ł
    -0.13
    POSITIVE LOGITS
     IonicPage
    0.16
    akis
    0.15
    ords
    0.14
    ajs
    0.14
    783
    0.13
    CFG
    0.13
    itize
    0.13
    346
    0.13
    lam
    0.13
    .gif
    0.13
    Act Density 0.045%

    No Known Activations