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

    Neuronpedia

    INDEX
    Explanations

    terms related to specificity and precision in descriptions or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.81
     Patro
    -0.72
     coals
    -0.70
    Mou
    -0.68
     serpent
    -0.66
    üyü
    -0.66
    onaise
    -0.64
     Bila
    -0.63
     crocodiles
    -0.63
     Gree
    -0.63
    POSITIVE LOGITS
     specific
    1.27
     SPECIFIC
    1.21
     Specific
    1.18
    specific
    1.13
    pecific
    1.10
    Specific
    1.08
    SPECIFIC
    1.05
     spesifik
    1.03
     particular
    1.02
     specifically
    1.00
    Act Density 0.117%

    No Known Activations