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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "none" or similar phrases indicating absence or null values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.69
    ward
    -0.65
     Swindon
    -0.64
    spit
    -0.63
     kring
    -0.63
     Draper
    -0.63
    Spiral
    -0.63
     Spitz
    -0.62
    paraíso
    -0.61
     Hayward
    -0.61
    POSITIVE LOGITS
     none
    1.54
    none
    1.47
    NONE
    1.43
     NONE
    1.37
    None
    1.29
     None
    1.25
     ninguno
    1.05
    nobody
    0.95
     nobody
    0.88
    +#+
    0.86
    Act Density 0.071%

    No Known Activations