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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "across" in various contexts and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulin
    -0.18
    ls
    -0.17
    áºŃt
    -0.16
    kenin
    -0.15
    agna
    -0.15
     gì
    -0.15
    éĤ£ç§į
    -0.14
    μιο
    -0.14
    thing
    -0.13
    è²¼
    -0.13
    POSITIVE LOGITS
    -the
    0.19
     spectrum
    0.18
    enger
    0.17
     across
    0.17
     Across
    0.16
    agate
    0.16
    Across
    0.16
    fid
    0.15
    uum
    0.15
    cut
    0.15
    Act Density 0.027%

    No Known Activations