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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives that describe actions or qualities with intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ultimately
    -0.18
    ityEngine
    -0.16
     полноÑģÑĤÑĮÑİ
    -0.16
    ãģµ
    -0.16
     ÑĥÑģпеÑĪ
    -0.16
     realmente
    -0.15
     поÑģÑĤеп
    -0.15
     легко
    -0.15
     ÑĤÑī
    -0.15
    metic
    -0.15
    POSITIVE LOGITS
     and
    0.28
     yet
    0.19
     but
    0.18
     enough
    0.18
    tics
    0.17
    mente
    0.15
     (?)
    0.15
    yet
    0.15
     и
    0.14
    /random
    0.14
    Act Density 0.182%

    No Known Activations