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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laikā
    -0.45
     személy
    -0.37
     Relaciones
    -0.36
     Selatan
    -0.35
     continúas
    -0.35
     Personen
    -0.33
     hinein
    -0.33
     personer
    -0.33
     fournisse
    -0.33
     modalités
    -0.33
    POSITIVE LOGITS
    EndContext
    0.61
    UrlResolution
    0.60
     otomatig
    0.55
     estekak
    0.53
    featureID
    0.52
     fuckin
    0.51
    Cyfeiriadau
    0.50
     goddamn
    0.50
     filthy
    0.50
     nukes
    0.50
    Act Density 1.189%

    No Known Activations