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

    Neuronpedia

    INDEX
    Explanations

    references to financial obligations and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elen
    -0.16
    owski
    -0.15
    ennes
    -0.15
    aus
    -0.14
    positor
    -0.14
    Aus
    -0.13
    лан
    -0.13
    áºŃm
    -0.13
    angkan
    -0.13
    ATCH
    -0.13
    POSITIVE LOGITS
     ÙĨÙĤد
    0.17
     sinking
    0.16
     ann
    0.16
     rental
    0.16
     rent
    0.16
     PS
    0.16
    uchen
    0.16
     assessments
    0.15
     premium
    0.15
     legacy
    0.15
    Act Density 0.060%

    No Known Activations