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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or differences in various quantities or attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical measurements and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alive
    -0.63
     unlimited
    -0.62
     Riv
    -0.61
    boss
    -0.58
     classy
    -0.56
     Gaga
    -0.56
     limitless
    -0.56
    safe
    -0.55
    cott
    -0.55
    cheat
    -0.54
    POSITIVE LOGITS
     attributable
    0.99
    ahime
    0.96
     compared
    0.92
     caused
    0.89
     between
    0.89
    Footnote
    0.83
     due
    0.82
     occurring
    0.81
     responsiveness
    0.81
     effected
    0.80
    Act Density 0.287%

    No Known Activations