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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mojom
    -0.16
    _EMIT
    -0.15
    ¾ç¤º
    -0.14
    porno
    -0.14
    'gc
    -0.14
     PaÅŁa
    -0.14
    ranÃŃ
    -0.13
     Flush
    -0.13
    ulp
    -0.13
    ãģĦãģŁ
    -0.13
    POSITIVE LOGITS
     Gus
    0.17
     jugg
    0.17
     turned
    0.17
     inventor
    0.16
     kept
    0.16
     Pey
    0.15
     given
    0.15
     taken
    0.15
     stolen
    0.14
     accessed
    0.14
    Act Density 0.456%

    No Known Activations