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
     Hoy
    -0.68
     Gentleman
    -0.64
     Landing
    -0.64
     Saud
    -0.63
    ffe
    -0.62
    ctors
    -0.62
    ainers
    -0.62
     Artists
    -0.62
     Cheong
    -0.61
     Hust
    -0.61
    POSITIVE LOGITS
     remotely
    0.84
     conducive
    0.79
    fit
    0.74
     otherwise
    0.74
    cedented
    0.73
     vaguely
    0.71
     suitable
    0.70
     wholly
    0.69
     antit
    0.69
     suited
    0.68
    Act Density 0.339%

    No Known Activations