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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    words related to horses or equine themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.69
    rylic
    -0.68
     ginger
    -0.64
    esters
    -0.62
     meticulously
    -0.61
    ists
    -0.61
    onym
    -0.60
     unintentionally
    -0.60
     unknow
    -0.59
     subconscious
    -0.57
    POSITIVE LOGITS
    orse
    1.06
    ments
    0.94
    lihood
    0.86
    MENTS
    0.85
     Reincarn
    0.82
    ment
    0.78
    ãĥĨ
    0.76
    ा
    0.74
    manship
    0.73
    MENT
    0.70
    Act Density 0.007%

    No Known Activations