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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and the integration of phrases related to complex concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aná
    -0.16
    ymi
    -0.14
    ugins
    -0.14
     ged
    -0.14
    anlı
    -0.13
    emen
    -0.13
    _tac
    -0.13
    @dynamic
    -0.13
    ･･
    -0.13
    .decorators
    -0.13
    POSITIVE LOGITS
     hatta
    0.15
     even
    0.15
     downright
    0.15
    etc
    0.14
     etc
    0.14
    lij
    0.14
    -most
    0.14
    rd
    0.14
    even
    0.14
    rog
    0.14
    Act Density 0.125%

    No Known Activations