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

    Neuronpedia

    INDEX
    Explanations

    references to community involvement and support for vulnerable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Must
    -0.15
    anvas
    -0.15
    Canonical
    -0.15
    agar
    -0.14
     korum
    -0.14
    haven
    -0.13
    곡
    -0.13
    Were
    -0.13
     Haven
    -0.13
    eceÄŁini
    -0.13
    POSITIVE LOGITS
     can
    1.14
    can
    0.85
    åı¯ä»¥
    0.83
    	can
    0.68
    Can
    0.68
     можно
    0.65
    .can
    0.65
     could
    0.65
     Can
    0.65
    ï¼Įåı¯ä»¥
    0.63
    Act Density 1.834%

    No Known Activations