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

    Neuronpedia

    INDEX
    Explanations

    expressions related to communication and expression of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -1.02
    IUrlHelper
    -0.84
     purpoſe
    -0.79
     Jefus
    -0.79
    fjspx
    -0.79
     <",
    -0.76
     समीक्षाओं
    -0.75
     <=",
    -0.70
    IntentFilter
    -0.70
     whoſe
    -0.70
    POSITIVE LOGITS
     speak
    1.26
     speaks
    1.22
    speak
    0.97
     Speak
    0.94
     speaking
    0.86
     spoke
    0.86
     Speaks
    0.82
    Speak
    0.77
     berbicara
    0.75
    speaking
    0.71
    Act Density 0.141%

    No Known Activations