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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online interactions and digital communication environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мил
    -0.15
    òi
    -0.15
    akah
    -0.14
    ÐĽÐŀ
    -0.14
    _LSB
    -0.14
    iyan
    -0.14
    =-=-
    -0.14
    omik
    -0.14
    PELL
    -0.14
    Ñĵ
    -0.13
    POSITIVE LOGITS
     rather
    0.17
    arrow
    0.16
     instead
    0.16
     or
    0.15
    edy
    0.15
    ãģ§ãģ¯ãģªãģı
    0.14
     Rather
    0.14
    ety
    0.14
     directly
    0.14
    973
    0.14
    Act Density 0.180%

    No Known Activations