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

    Neuronpedia

    INDEX
    Explanations

    unique start tokens or indicators that signify the beginning of segments or moments in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.62
    featureID
    -0.61
     dren
    -0.60
     NSCoder
    -0.58
    exitRule
    -0.56
    تقاوى
    -0.54
    LError
    -0.54
     jú
    -0.54
     dAtA
    -0.54
    UTH
    -0.53
    POSITIVE LOGITS
    __(/*!
    0.83
    elaar
    0.71
    )\\
    0.67
    )}}
    0.67
     GoogleFonts
    0.65
    cosse
    0.64
    sunami
    0.64
    …)
    0.63
     …)
    0.62
    ')")
    0.62
    Act Density 0.038%

    No Known Activations