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

    Neuronpedia

    INDEX
    Explanations

    specific non-English characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    653
    -0.16
    ardon
    -0.14
    zz
    -0.14
    nger
    -0.14
     writable
    -0.14
    optera
    -0.14
    blings
    -0.14
    zeÅĪ
    -0.14
    arrant
    -0.13
    ноÑģÑĤÑĸ
    -0.13
    POSITIVE LOGITS
    ¼
    0.20
    Ħ
    0.19
    ¸
    0.16
    ´
    0.15
    Ģ
    0.14
    dorf
    0.14
    haps
    0.14
    ally
    0.14
    ï¸ı
    0.14
     SHARES
    0.14
    Act Density 0.009%

    No Known Activations