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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and academic theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itude
    -0.18
    ello
    -0.17
    stones
    -0.17
    itan
    -0.16
    ellan
    -0.16
    ned
    -0.16
    ening
    -0.16
    own
    -0.15
    engers
    -0.15
    acre
    -0.15
    POSITIVE LOGITS
    ically
    0.18
    rence
    0.17
    /pr
    0.16
    czy
    0.16
    779
    0.16
     پرداز
    0.16
    ical
    0.15
    838
    0.15
    /model
    0.15
    ICAL
    0.15
    Act Density 0.026%

    No Known Activations