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

    Neuronpedia

    INDEX
    Explanations

    key nouns and phrases indicating processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alt
    -0.17
     Alt
    -0.17
    ac
    -0.17
    im
    -0.16
     rel
    -0.15
    ame
    -0.15
     fest
    -0.15
    Bulk
    -0.15
    -0.14
    inder
    -0.14
    POSITIVE LOGITS
    thinkable
    0.17
    elijk
    0.17
    /lic
    0.15
    uada
    0.15
    azers
    0.15
     íĶĦ리
    0.15
    æ¦
    0.15
    TRGL
    0.15
    _READONLY
    0.15
    bers
    0.15
    Act Density 0.009%

    No Known Activations