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

    Neuronpedia

    INDEX
    Explanations

    references to self-identity and subjective experience

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

    First-person references and speech

    np_acts-logits-general · gemini-2.0-flash

    referring to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.76
     resourceCulture
    -0.74
     समीक्षाओं
    -0.73
    PerformLayout
    -0.71
    writeFieldEnd
    -0.64
    
    -0.64
     EconPapers
    -0.63
    phorus
    -0.63
    ContentAsync
    -0.62
    :✨
    -0.61
    POSITIVE LOGITS
     referring
    1.89
     talking
    1.78
     speaking
    1.58
     refer
    1.50
    refer
    1.41
     refers
    1.41
    talking
    1.41
     Talking
    1.35
     Referring
    1.35
    speaking
    1.34
    Act Density 0.257%

    No Known Activations