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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "other" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -equiv
    -0.16
    OfYear
    -0.14
    bÃŃr
    -0.14
    æĪIJ人
    -0.14
    ÑĢина
    -0.14
    zcze
    -0.14
     Seks
    -0.13
    ENCIL
    -0.13
    ëįĶëĭĪ
    -0.13
    atic
    -0.13
    POSITIVE LOGITS
     ones
    0.23
    ones
    0.19
    maal
    0.19
     Ones
    0.15
    ONES
    0.15
    chter
    0.15
     others
    0.14
    ôm
    0.14
    jen
    0.14
    åij¢
    0.14
    Act Density 0.045%

    No Known Activations