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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly various quotation marks and apostrophes

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

    quoted words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dafx
    -0.68
     HasFactory
    -0.63
     feroit
    -0.62
     pouvoit
    -0.60
     '\\;'
    -0.59
    pecabe
    -0.58
     étoit
    -0.58
     étoient
    -0.58
    GEBURTS
    -0.57
    ésult
    -0.57
    POSITIVE LOGITS
    quitous
    0.50
     unconventional
    0.49
     substantial
    0.49
     alternative
    0.47
    மான
    0.46
     Substantial
    0.46
    private
    0.45
     modest
    0.44
     legitimate
    0.44
     private
    0.44
    Act Density 0.068%

    No Known Activations