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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    embro
    -0.17
    ÑĢаÑĩ
    -0.15
    etat
    -0.15
    AGMA
    -0.15
    eta
    -0.14
    ewire
    -0.14
    engin
    -0.14
    ugi
    -0.14
    reature
    -0.14
    cka
    -0.14
    POSITIVE LOGITS
     well
    0.51
    well
    0.41
     wel
    0.39
    -w
    0.38
    wel
    0.36
     wells
    0.30
    lo
    0.29
     WELL
    0.26
     weil
    0.25
     welt
    0.25
    Act Density 0.027%

    No Known Activations