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

    Neuronpedia

    INDEX
    Explanations

    words related to technical terms and procedures

    oai_token-act-pair · gpt-3.5-turbo

    compound words or elements related to collaboration and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.89
    enegger
    -0.76
     Immunity
    -0.68
     Palo
    -0.67
    è£ħ
    -0.66
     Wilde
    -0.65
     Kali
    -0.65
    è¦ļéĨĴ
    -0.64
    SHARE
    -0.63
     Elves
    -0.62
    POSITIVE LOGITS
    ruction
    1.12
    acters
    1.06
    tenance
    0.97
    oldown
    0.97
    ility
    0.96
    ipment
    0.94
    artment
    0.92
    istance
    0.90
    perature
    0.88
    anced
    0.88
    Act Density 0.160%

    No Known Activations