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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    morgan
    -0.17
    ebek
    -0.16
    oš
    -0.16
    CHANT
    -0.16
    опол
    -0.15
     aalborg
    -0.15
    aravel
    -0.15
    ména
    -0.15
     Erotische
    -0.15
    osti
    -0.15
    POSITIVE LOGITS
     given
    0.18
    475
    0.17
    462
    0.17
     prevailed
    0.16
    iro
    0.16
     brought
    0.15
     persistent
    0.15
     taken
    0.15
     told
    0.15
     forced
    0.15
    Act Density 0.208%

    No Known Activations