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

    Neuronpedia

    INDEX
    Explanations

    references to purpose and personal motivation

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

    cliches and hype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.34
     corto
    -0.33
     ģ
    -0.33
    parsedMessage
    -0.31
     يل
    -0.28
     обли
    -0.27
     coar
    -0.27
    IALLY
    -0.26
     tor
    -0.26
     &___
    -0.26
    POSITIVE LOGITS
     cliche
    0.67
    hoeddwyd
    0.66
     cliché
    0.65
    jsxFileName
    0.65
     hype
    0.62
     kasarigan
    0.60
     clichés
    0.60
     hyped
    0.60
     ब्रेकडाउन
    0.59
     bullshit
    0.58
    Act Density 0.111%

    No Known Activations