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

    Neuronpedia

    INDEX
    Explanations

    references to double-digit numerical values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouf
    -0.80
    hire
    -0.78
    dep
    -0.74
    nd
    -0.72
    erker
    -0.72
    enes
    -0.72
    rael
    -0.71
    low
    -0.71
    rup
    -0.71
    lain
    -0.70
    POSITIVE LOGITS
    ized
    0.92
    omial
    0.91
    ised
    0.90
    itialized
    0.88
    ally
    0.86
     digits
    0.83
    igr
    0.83
    ographic
    0.82
    umeric
    0.82
    ization
    0.82
    Act Density 0.031%

    No Known Activations