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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    |()
    -0.58
    illary
    -0.57
     pared
    -0.50
    witter
    -0.50
    assioned
    -0.49
     ostensibly
    -0.49
     glean
    -0.49
     devrez
    -0.49
    Conversely
    -0.48
     incen
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.79
     advices
    0.73
    osoever
    0.65
     كومونز
    0.63
     having
    0.63
     متعلقه
    0.63
     loosing
    0.61
     equipments
    0.61
     sufferings
    0.59
    šanai
    0.59
    Act Density 0.831%

    No Known Activations