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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.87
     myſelf
    -0.86
     itſelf
    -0.85
     themſelves
    -0.83
     poffe
    -0.83
     purpoſe
    -0.80
     raiſ
    -0.80
     pleaſure
    -0.79
     ―――――
    -0.76
     faſt
    -0.76
    POSITIVE LOGITS
     be
    0.66
    idov
    0.60
    ביוגרפיה
    0.60
     Sh
    0.59
     have
    0.59
     run
    0.59
     跳转至
    0.59
     may
    0.57
     not
    0.57
     further
    0.57
    Act Density 0.048%

    No Known Activations