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

    Neuronpedia

    INDEX
    Explanations

    instances of strong opinions or compelling arguments in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uncategorized
    -0.17
    bject
    -0.15
    ëį°ìĿ´íĬ¸
    -0.14
     ëĦ¤ìĿ´íĬ¸
    -0.14
    deaux
    -0.14
    ekim
    -0.13
    buat
    -0.13
    ãĥ»ãĥ»ãĥ»↵↵
    -0.13
    engin
    -0.13
    erif
    -0.13
    POSITIVE LOGITS
     [âĢ¦]
    0.30
     [âĢ¦
    0.28
    [,]
    0.26
     [=
    0.24
    [s
    0.24
     [_
    0.21
     [
    0.21
     [âĢ¦]↵
    0.20
     [...]
    0.20
     [`
    0.20
    Act Density 6.970%

    No Known Activations