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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quotes or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ach
    -0.16
    enta
    -0.15
    ime
    -0.15
    ãĥĨãĥ«
    -0.15
    ault
    -0.15
    imb
    -0.14
    agar
    -0.14
    èĥŀ
    -0.14
    æ´ģ
    -0.14
    irc
    -0.13
    POSITIVE LOGITS
    kker
    0.18
    ÅĻÃŃž
    0.17
    sert
    0.16
    olina
    0.16
    lify
    0.15
    ication
    0.15
    ISIBLE
    0.15
    ãĢ
    0.14
    cke
    0.14
    ırak
    0.14
    Act Density 0.110%

    No Known Activations