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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a portion or composition of a group or population

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups or segments of a population

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     renew
    -0.77
    rought
    -0.71
    isSpecialOrderable
    -0.71
    aughs
    -0.68
     authored
    -0.68
     foresee
    -0.67
    seek
    -0.67
     thefts
    -0.66
     reprint
    -0.65
    earances
    -0.65
    POSITIVE LOGITS
     backbone
    1.03
     nucleus
    0.99
     basis
    0.95
     majority
    0.83
     mosaic
    0.79
     bulk
    0.74
     bul
    0.72
     cornerstone
    0.71
    ãĤ§
    0.70
     semic
    0.69
    Act Density 0.130%

    No Known Activations