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

    Neuronpedia

    INDEX
    Explanations

    details and specifications related to procedures and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.79
     Monfieur
    -0.78
     tomorrow
    -0.75
     theſe
    -0.73
     attualmente
    -0.73
     derzeit
    -0.71
     Cæsar
    -0.70
    attuale
    -0.70
     pleaſure
    -0.70
     amanhã
    -0.69
    POSITIVE LOGITS
     wasn
    0.95
     was
    0.94
     didn
    0.93
     Wasn
    0.86
     did
    0.84
     damals
    0.83
     went
    0.82
    Wasn
    0.80
     originally
    0.80
     ayer
    0.78
    Act Density 4.181%

    No Known Activations