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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that convey a sense of magnitude or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eco
    -0.17
    ekim
    -0.16
    strup
    -0.15
    cono
    -0.14
    embre
    -0.14
    flows
    -0.14
    unday
    -0.14
    acity
    -0.14
    าà¸ĩว
    -0.14
     Franken
    -0.14
    POSITIVE LOGITS
    ickle
    0.18
    ingly
    0.16
    olland
    0.15
    ocup
    0.15
    anned
    0.15
    á»įt
    0.15
    iked
    0.15
    ByExample
    0.14
    xffffffff
    0.14
    ned
    0.14
    Act Density 0.102%

    No Known Activations