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

    Neuronpedia

    INDEX
    Explanations

    mentions of high proportions or very large quantities of something

    oai_token-act-pair · gpt-3.5-turbo

    references to a large proportion or segment of a group or population

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.69
    uras
    -0.65
    LV
    -0.63
    spir
    -0.62
    ilion
    -0.60
    ogens
    -0.59
    into
    -0.59
     Frenzy
    -0.58
     majesty
    -0.58
    agate
    -0.58
    POSITIVE LOGITS
     of
    0.80
     shareholder
    0.77
     thereof
    0.76
     (>
    0.75
     (~
    0.66
     sticking
    0.66
    erer
    0.66
    ONE
    0.65
    body
    0.65
     opinion
    0.65
    Act Density 0.024%

    No Known Activations