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

    Neuronpedia

    INDEX
    Explanations

    statements of importance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.17
    isas
    -0.16
    ish
    -0.16
    chet
    -0.15
    PT
    -0.15
    yang
    -0.14
    verse
    -0.14
    ÐĶÐļ
    -0.14
    irl
    -0.14
    WSC
    -0.14
    POSITIVE LOGITS
    ingleton
    0.16
    chrift
    0.15
    Ïĥη
    0.15
     point
    0.14
    erus
    0.14
    ington
    0.14
    /max
    0.14
    ritt
    0.14
    AO
    0.14
    alat
    0.14
    Act Density 0.041%

    No Known Activations