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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "speak" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    speaking

    np_acts-logits-general · gemini-2.0-flash

    the act of speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vario
    -0.50
    ValueStyle
    -0.50
     Margo
    -0.48
    SuppressLint
    -0.48
     lazily
    -0.47
     Maroon
    -0.47
     Jor
    -0.46
    anganese
    -0.46
     Jira
    -0.46
     RUT
    -0.46
    POSITIVE LOGITS
     speak
    1.80
     speaking
    1.79
     spoke
    1.70
     speaks
    1.70
     Speak
    1.60
     spoken
    1.57
    speaking
    1.56
    Speak
    1.55
    speak
    1.51
     Speaking
    1.51
    Act Density 0.083%

    No Known Activations