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

    Neuronpedia

    INDEX
    Explanations

    words related to being plain and elected officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.94
     myſelf
    -0.92
     itſelf
    -0.90
    ".
    -0.89
    NUMX
    -0.87
    ſelf
    -0.84
     himſelf
    -0.80
     fhew
    -0.80
     poffe
    -0.79
     iſt
    -0.79
    POSITIVE LOGITS
    plain
    0.68
     plain
    0.58
    enrollment
    0.57
    Plain
    0.56
     çe
    0.54
     Enrollment
    0.54
     enrolled
    0.54
     tarifas
    0.53
     ttk
    0.52
    خ
    0.52
    Act Density 0.129%

    No Known Activations