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

    Neuronpedia

    INDEX
    Explanations

    frequent articles and pronouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anza
    -0.16
    culos
    -0.15
    izedName
    -0.15
    bert
    -0.15
    ansen
    -0.15
    ano
    -0.14
    ENCH
    -0.14
    encent
    -0.14
    isan
    -0.13
    ÌĢ
    -0.13
    POSITIVE LOGITS
     Lud
    0.17
    Mine
    0.14
    ahead
    0.14
    è¼
    0.14
     Dud
    0.14
     Mort
    0.14
    ered
    0.14
     alike
    0.13
    ìłĢ
    0.13
    vey
    0.13
    Act Density 0.233%

    No Known Activations