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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himo
    -0.61
     zijne
    -0.59
     '{@
    -0.58
     bestehende
    -0.56
     bestaande
    -0.55
     mijne
    -0.54
     незавершена
    -0.54
    Rohy
    -0.53
     äldre
    -0.52
     sukker
    -0.52
    POSITIVE LOGITS
    CrossRef
    0.75
     also
    0.62
     is
    0.62
    AutoScale
    0.62
     विश्वसनीयता
    0.57
     always
    0.56
    approche
    0.56
    SequentialGroup
    0.56
     finally
    0.54
     was
    0.54
    Act Density 0.634%

    No Known Activations