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

    Neuronpedia

    INDEX
    Explanations

    words related to large size or scale

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "meg" or variations of it, likely related to concepts surrounding significant quantities or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.71
     Continued
    -0.71
     humour
    -0.68
     Sense
    -0.65
     Grounds
    -0.65
     condition
    -0.64
    xtap
    -0.64
    unct
    -0.61
     Taste
    -0.61
     Paradox
    -0.61
    POSITIVE LOGITS
    abyte
    1.48
    abytes
    1.45
    apixel
    1.24
    awatts
    1.19
    acity
    1.14
    abases
    1.13
    atis
    1.07
    atron
    1.06
    aton
    1.04
    abit
    1.03
    Act Density 0.042%

    No Known Activations