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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or possibilities related to events and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andas
    -0.17
     have
    -0.16
    alu
    -0.15
    -pdf
    -0.15
     almost
    -0.15
     Joel
    -0.14
     mos
    -0.14
    æĺĵ
    -0.14
     last
    -0.14
     ks
    -0.14
    POSITIVE LOGITS
    ftime
    0.18
     tomorrow
    0.16
    ÑĹ
    0.16
    @brief
    0.15
     Tomorrow
    0.15
    orian
    0.15
    .sax
    0.15
    ìŀ¡
    0.14
    eel
    0.14
    _OPTS
    0.14
    Act Density 0.198%

    No Known Activations