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

    Neuronpedia

    INDEX
    Explanations

    the word "above"

    oai_token-act-pair · gpt-4-turbo

    instances where the phrase "the above" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to preceding information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ring
    -0.77
     CTR
    -0.74
     Centers
    -0.69
    Wheel
    -0.66
    Mail
    -0.65
    Access
    -0.65
    assian
    -0.65
     Instruments
    -0.63
    Sport
    -0.63
    dll
    -0.61
    POSITIVE LOGITS
    ground
    0.87
    above
    0.85
    perty
    0.82
     above
    0.81
     Above
    0.78
    uckland
    0.76
    hetically
    0.76
    ceed
    0.73
    mentioned
    0.73
    Above
    0.71
    Act Density 0.020%

    No Known Activations