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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    recision
    -0.16
    ceb
    -0.15
    ollah
    -0.15
    _accessible
    -0.14
    еÑĢÑĮ
    -0.14
    urma
    -0.14
    ÑĢеп
    -0.14
    kah
    -0.14
    oston
    -0.13
    ovable
    -0.13
    POSITIVE LOGITS
     to
    0.18
     help
    0.17
     lunch
    0.16
    ilon
    0.16
    ansen
    0.16
     final
    0.15
    ãĥªãĥ³ãĤ°
    0.15
    aging
    0.15
     photographs
    0.15
     photos
    0.14
    Act Density 0.084%

    No Known Activations