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

    Neuronpedia

    INDEX
    Explanations

    references to specific fictional characters and titles within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.68
    WriteAttribute
    -0.60
     ſont
    -0.56
     '\\;'
    -0.56
    styleType
    -0.55
     مرئيه
    -0.54
    .*")]
    -0.53
     Svg
    -0.53
    ſelben
    -0.52
    WriteBarrier
    -0.52
    POSITIVE LOGITS
     Jedi
    0.50
    Jedi
    0.43
    Lähteet
    0.41
     jedi
    0.41
     lightsaber
    0.40
     Sith
    0.33
     ciudadano
    0.31
    patine
    0.31
     człowie
    0.30
     détruire
    0.29
    Act Density 0.420%

    No Known Activations