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

    Neuronpedia

    INDEX
    Explanations

    symbols related to mathematical expressions or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     came
    -0.62
    ")){
    -0.61
    /";
    -0.59
    _
    -0.58
    "):
    -0.57
    "){
    -0.56
    """,
    -0.56
    +
    -0.54
    \)
    -0.54
    </em>
    -0.53
    POSITIVE LOGITS
     Majefty
    0.97
     piele
    0.73
     насељу
    0.72
     purpoſe
    0.71
     inimes
    0.71
     Antiquity
    0.70
     pleaſure
    0.69
     reaſon
    0.69
     houſe
    0.69
     picioare
    0.69
    Act Density 1.460%

    No Known Activations