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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes

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

    opening quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.55
    EDEFAULT
    -0.48
     Landschafts
    -0.48
     uș
    -0.47
    }[!
    -0.46
    clearpage
    -0.45
    horabuena
    -0.44
    pulseira
    -0.43
     ErrInvalid
    -0.43
    Демографія
    -0.42
    POSITIVE LOGITS
    Chham
    0.50
    おきます
    0.43
     Compound
    0.42
     phrases
    0.42
     “
    0.40
     beads
    0.40
     persian
    0.40
    oplayer
    0.40
    ‘
    0.39
     letters
    0.38
    Act Density 0.106%

    No Known Activations