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

    Neuronpedia

    INDEX
    Explanations

    punctuation, line breaks, and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urge
    -0.16
    imen
    -0.16
     nid
    -0.16
    yer
    -0.15
    nid
    -0.15
    веÑĢд
    -0.14
    immel
    -0.14
    ÄĻki
    -0.14
    Ậ
    -0.14
    abel
    -0.14
    POSITIVE LOGITS
    fst
    0.17
    jez
    0.15
    ARA
    0.15
    Ear
    0.14
    /environment
    0.13
    ogg
    0.13
    ãģĵãĤĵãģ«
    0.13
    adow
    0.13
    ?(:
    0.13
    ¦
    0.13
    Act Density 0.002%

    No Known Activations