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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "speak" and its variations, indicating discussions or expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.84
     تضيفلها
    -0.76
    DoubleQuotes
    -0.75
    دانشنامهٔ
    -0.72
    Попис
    -0.72
     greateſt
    -0.69
     actionMode
    -0.67
    tagHelperRunner
    -0.67
    actionMode
    -0.66
     clearColor
    -0.65
    POSITIVE LOGITS
     speak
    0.92
     speaks
    0.89
     speaking
    0.85
     spoke
    0.85
     Speak
    0.78
    Speaking
    0.78
     Speaking
    0.77
    Speak
    0.75
     Speaks
    0.74
    SPE
    0.73
    Act Density 0.047%

    No Known Activations