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

    Neuronpedia

    INDEX
    Explanations

    references to tutorials and learning resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     komende
    -0.45
     handen
    -0.40
     afspraak
    -0.39
     vloer
    -0.38
     voren
    -0.38
     zijne
    -0.38
     mijne
    -0.37
     prijzen
    -0.36
     bevol
    -0.36
     smtplib
    -0.36
    POSITIVE LOGITS
     très
    0.79
     bien
    0.69
     particuli
    0.64
     assez
    0.63
     fort
    0.61
     plus
    0.60
     toujours
    0.58
     extrêmement
    0.58
    très
    0.57
    Très
    0.57
    Act Density 0.152%

    No Known Activations