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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gus
    -0.91
     Gus
    -0.84
    fich
    -0.73
     Scherer
    -0.70
    parsedMessage
    -0.69
    Hermione
    -0.68
    Stalin
    -0.67
     Gres
    -0.67
    trainable
    -0.66
    Angelina
    -0.66
    POSITIVE LOGITS
     pleaſure
    0.89
     perſon
    0.88
     위해
    0.86
     purpoſe
    0.85
     ſame
    0.84
     ſever
    0.84
     myſelf
    0.83
     beſt
    0.82
     ſtate
    0.80
     houſe
    0.77
    Act Density 0.111%

    No Known Activations