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
    ienes
    -0.15
    çļĦæĺ¯
    -0.15
    dana
    -0.15
    ps
    -0.15
    FSIZE
    -0.14
    代
    -0.14
    nett
    -0.14
    hawks
    -0.14
    816
    -0.13
    ibel
    -0.13
    POSITIVE LOGITS
    ugen
    0.13
     cosm
    0.13
    SURE
    0.13
    itom
    0.13
     som
    0.13
    otel
    0.13
     Jerome
    0.13
    aba
    0.12
    [assembly
    0.12
    uble
    0.12
    Act Density 0.076%

    No Known Activations