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

    Neuronpedia

    INDEX
    Explanations

    headings and formatting elements indicating sections or lists in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiro
    -0.08
    ISTA
    -0.07
    heed
    -0.07
    hea
    -0.07
    Bias
    -0.07
    aday
    -0.07
    ear
    -0.07
    (disposing
    -0.07
    ctor
    -0.07
    æ¯
    -0.07
    POSITIVE LOGITS
     what
    0.10
     why
    0.09
     beyond
    0.09
     another
    0.08
     where
    0.08
     not
    0.08
     opportunity
    0.08
     who
    0.08
     an
    0.08
     a
    0.08
    Act Density 0.027%

    No Known Activations