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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific processes or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -1.76
    ment
    -1.17
    logy
    -1.14
    ity
    -1.05
    ATION
    -0.96
    ction
    -0.91
    ology
    -0.90
    nastics
    -0.84
    ism
    -0.76
     autorytatywna
    -0.75
    POSITIVE LOGITS
    hips
    1.16
    ations
    0.85
    nesses
    0.77
    ments
    0.75
    ATIONS
    0.69
    ages
    0.64
    ating
    0.63
    ungen
    0.62
    ulations
    0.59
    ghijklmnop
    0.59
    Act Density 0.657%

    No Known Activations