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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "be"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ethene
    -0.65
    ņem
    -0.63
     Hermans
    -0.63
     trebuie
    -0.62
    TimeTo
    -0.62
     cokelat
    -0.61
     phospho
    -0.61
     africain
    -0.59
    OTION
    -0.59
     πρέπει
    -0.57
    POSITIVE LOGITS
    Sucesor
    0.82
    expandindo
    0.77
    исленность
    0.76
    OGND
    0.75
     propOrder
    0.75
    ViewFeatures
    0.69
    EndContext
    0.69
    KURZBESCHREIBUNG
    0.69
    upi
    0.68
    KommentareTeilen
    0.67
    Act Density 0.059%

    No Known Activations