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

    Neuronpedia

    INDEX
    Explanations

    references to iconic characters and figures in popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tamment
    -0.58
    édez
    -0.57
    RegressionTest
    -0.57
    Jeografia
    -0.56
    MessageOf
    -0.55
    tagext
    -0.51
    PageContext
    -0.51
    Склад
    -0.50
     Boer
    -0.50
     kasarigan
    -0.50
    POSITIVE LOGITS
     himself
    0.89
     Himself
    0.84
    himself
    0.73
     himſelf
    0.69
    tagHelperRunner
    0.68
    springframework
    0.61
    whom
    0.60
    gebob
    0.59
     Superman
    0.56
    Superman
    0.56
    Act Density 0.056%

    No Known Activations