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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.70
     ergo
    -0.69
     myſelf
    -0.69
     Anſ
    -0.68
     Indoch
    -0.67
     GetEnumerator
    -0.66
    Hochspringen
    -0.66
     leſs
    -0.65
     Diſ
    -0.65
     MSD
    -0.65
    POSITIVE LOGITS
     barely
    0.85
     even
    0.85
     siquiera
    0.78
    principalTable
    0.71
     Even
    0.69
     EVEN
    0.67
    InputBorder
    0.65
     half
    0.62
     eens
    0.61
    even
    0.60
    Act Density 0.095%

    No Known Activations