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

    Neuronpedia

    INDEX
    Explanations

    patterns related to procedural or algorithmic steps in a coding or data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ°ãģĭãĤĬ
    -0.15
    nik
    -0.15
    wort
    -0.15
    **
    -0.13
    bis
    -0.13
     (!((
    -0.13
    ichtet
    -0.13
    mentions
    -0.13
     contextual
    -0.13
    ienne
    -0.12
    POSITIVE LOGITS
    Č
    0.17
    945
    0.17
    751
    0.15
    oggler
    0.15
    Bomb
    0.14
    -navigation
    0.14
    èĤ²
    0.14
    keh
    0.14
     Bard
    0.14
    foon
    0.14
    Act Density 0.019%

    No Known Activations