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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estacks
    -0.47
    <eos>
    -0.46
    ">//
    -0.44
    [--
    -0.42
     indictment
    -0.41
     zorgen
    -0.41
    bParam
    -0.40
     Teufel
    -0.40
     breaking
    -0.40
    kými
    -0.40
    POSITIVE LOGITS
    بوابة
    0.80
    awtextra
    0.79
    rungsseite
    0.73
     '{@
    0.70
     MainAxisSize
    0.70
    पया
    0.66
    verwijspagina
    0.64
    izze
    0.63
    SPATH
    0.63
    AndEndTag
    0.60
    Act Density 0.061%

    No Known Activations