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

    Neuronpedia

    INDEX
    Explanations

    numbers with 'w' in the middle

    oai_token-act-pair · gpt-3.5-turbo

    terms related to power generation and energy measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.87
    enegger
    -0.85
     Rabbit
    -0.74
     backstage
    -0.71
     Cha
    -0.67
     Bj
    -0.67
     Schwarzenegger
    -0.65
     Baal
    -0.63
     Reconstruction
    -0.61
     Scand
    -0.61
    POSITIVE LOGITS
    pload
    1.31
    atts
    1.18
    att
    1.10
    pees
    1.07
    uries
    1.02
    poons
    1.00
    illion
    0.97
    maximum
    0.96
    ixels
    0.91
    ounds
    0.91
    Act Density 0.042%

    No Known Activations