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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "equals" indicating comparisons or equality checks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychological
    -0.58
     Psychological
    -0.54
    Psychological
    -0.50
    ніципалі
    -0.48
     psicológico
    -0.47
    RectangleBorder
    -0.47
     mental
    -0.46
     psycholog
    -0.45
     psychologically
    -0.45
     mentale
    -0.44
    POSITIVE LOGITS
     either
    0.56
     Either
    0.54
    Either
    0.54
    either
    0.52
     GenerationType
    0.42
    ither
    0.41
    Elaboración
    0.41
     aDecoder
    0.40
    ].
    0.40
    toBeDefined
    0.40
    Act Density 0.066%

    No Known Activations