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

    Neuronpedia

    INDEX
    Explanations

    references to singular items or entities across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     >=",
    -0.73
    __*/
    -0.70
    帖最后由
    -0.70
    crites
    -0.67
    contentLoaded
    -0.67
    setAccessible
    -0.66
     يتيمه
    -0.64
    Rhestr
    -0.63
     ―――――
    -0.63
    romeda
    -0.62
    POSITIVE LOGITS
     single
    1.20
    single
    1.01
    Single
    0.96
     Single
    0.93
     SINGLE
    0.88
     tunggal
    0.88
     solitary
    0.83
    SINGLE
    0.77
     singular
    0.70
     duy
    0.67
    Act Density 0.398%

    No Known Activations