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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     Majefty
    -1.04
     itſelf
    -1.02
     Monfieur
    -1.01
     Efq
    -1.01
    ſelf
    -1.00
     pleaſure
    -0.97
     houſe
    -0.96
     himſelf
    -0.96
     Jefus
    -0.94
    POSITIVE LOGITS
     zwar
    0.57
     sud
    0.57
    NullCheck
    0.56
    SUD
    0.52
     und
    0.52
    </b>
    0.51
    /
    0.51
    quot
    0.50
    antino
    0.49
     I
    0.48
    Act Density 0.338%

    No Known Activations