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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a prolonged duration or historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sing
    -0.16
    chy
    -0.15
    gua
    -0.14
    inho
    -0.14
    ookie
    -0.14
    Ìģc
    -0.13
    åłĤ
    -0.13
    231
    -0.13
    isses
    -0.13
    agrant
    -0.13
    POSITIVE LOGITS
    ÅĻez
    0.16
    evity
    0.16
     been
    0.15
    TOT
    0.14
    ATAL
    0.14
     enough
    0.13
    rier
    0.13
     pup
    0.13
    ="../../../
    0.13
    reur
    0.13
    Act Density 0.025%

    No Known Activations