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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their affiliations or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dunlap
    -0.48
     fato
    -0.48
     dini
    -0.46
    Nbr
    -0.42
     Erickson
    -0.42
     rozs
    -0.40
     levé
    -0.40
     aktivitas
    -0.40
     tæn
    -0.39
     dej
    -0.39
    POSITIVE LOGITS
    0.89
     Efq
    0.87
     actionMode
    0.81
     Theſe
    0.79
     tartalomajánló
    0.79
     Ouv
    0.77
     myſelf
    0.76
     Monfieur
    0.74
    abestanden
    0.74
    ThroughAttribute
    0.73
    Act Density 0.238%

    No Known Activations