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

    Neuronpedia

    INDEX
    Explanations

    contexts associated with choices, consequences, and evaluations of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.61
    ChildScrollView
    -0.61
     CreateTagHelper
    -0.57
     WebDriverWait
    -0.53
    RTEX
    -0.52
    thansa
    -0.52
    :✨
    -0.52
    parsedMessage
    -0.49
     Majefty
    -0.49
    gonic
    -0.49
    POSITIVE LOGITS
     negative
    0.56
     negativos
    0.54
     negatives
    0.52
     négatif
    0.51
     negativo
    0.50
     negativas
    0.48
     failures
    0.47
     kötü
    0.47
    Negative
    0.46
     negatively
    0.45
    Act Density 0.558%

    No Known Activations