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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to significant or notable actions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cher
    -0.18
     çľ
    -0.17
     occasions
    -0.16
    ĥ½
    -0.16
    Å¡t
    -0.15
     occasion
    -0.14
     distraction
    -0.14
    .exc
    -0.14
    ëŀĢ
    -0.14
    ITU
    -0.13
    POSITIVE LOGITS
     tiên
    0.25
     thing
    0.16
    iasco
    0.16
     ardından
    0.15
    thing
    0.15
     priority
    0.15
     먼ìłĢ
    0.15
    hands
    0.14
    atte
    0.14
    hof
    0.14
    Act Density 0.051%

    No Known Activations