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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion and feelings about preferences

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

    expressing personal opinions and dislikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manufacturing
    -0.35
     verification
    -0.35
     confi
    -0.34
     Pioneers
    -0.34
     expectancy
    -0.34
     fidelity
    -0.33
     equipa
    -0.33
     Paglinawan
    -0.33
     Comp
    -0.33
     completion
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.58
    MessageOf
    0.57
    SequentialGroup
    0.57
    verwijspagina
    0.56
     dislike
    0.55
    ंदीखरीदारी
    0.54
    optionalTypeArgs
    0.52
    dislike
    0.52
    RegressionTest
    0.52
     prefier
    0.50
    Act Density 0.041%

    No Known Activations