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

    Neuronpedia

    INDEX
    Explanations

    the word "ors" with various digits preceding it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "ors" or possibly references to organizations and entities that have "ors" in their names or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctors
    -0.66
    Fra
    -0.65
    lyak
    -0.64
    ITNESS
    -0.64
    LET
    -0.64
    let
    -0.63
    ulative
    -0.62
    OTAL
    -0.62
     Upton
    -0.62
    esville
    -0.62
    POSITIVE LOGITS
    hips
    1.34
    hift
    1.06
    poons
    0.97
    pring
    0.93
    pace
    0.92
    mith
    0.91
    poon
    0.90
    pheus
    0.89
    hip
    0.86
    hin
    0.84
    Act Density 0.037%

    No Known Activations