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

    Neuronpedia

    INDEX
    Explanations

    the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antics
    -0.16
    á»ī
    -0.14
    aira
    -0.14
    ala
    -0.14
    ila
    -0.14
    apol
    -0.14
     Hud
    -0.14
    man
    -0.14
    stroy
    -0.14
    ick
    -0.14
    POSITIVE LOGITS
    ستر
    0.18
    ooter
    0.15
    bung
    0.15
     GOODMAN
    0.15
    werp
    0.15
    ayar
    0.14
    ätz
    0.14
     Goodman
    0.14
    ë¬¸ìłľ
    0.14
    .TestTools
    0.14
    Act Density 0.019%

    No Known Activations