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

    Neuronpedia

    INDEX
    Explanations

    references to a specific subject or entity, particularly the word "the."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.78
    ymce
    -0.74
    ftagPool
    -0.70
    Namara
    -0.68
    клопе
    -0.68
    uxxxx
    -0.67
    adaptiveStyles
    -0.66
     PyLong
    -0.66
    ureau
    -0.65
     Whitaker
    -0.64
    POSITIVE LOGITS
    GMENT
    0.59
    anganronpa
    0.55
    Said
    0.54
    findpost
    0.54
    Биография
    0.52
     obstante
    0.52
    例句
    0.52
     myſelf
    0.50
     Gout
    0.50
     mariner
    0.50
    Act Density 0.028%

    No Known Activations