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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inability or negation, particularly involving the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    could not + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Références
    -0.39
     inicios
    -0.39
    tênis
    -0.39
     gonna
    -0.39
    belongs
    -0.38
    łóż
    -0.37
    dealloc
    -0.37
    枉
    -0.37
    subpackage
    -0.36
     harms
    -0.36
    POSITIVE LOGITS
     could
    0.73
     Could
    0.69
    Could
    0.67
     couldnt
    0.64
    could
    0.64
     Couldn
    0.62
     kunde
    0.58
     couldn
    0.57
    Couldn
    0.56
     COULD
    0.56
    Act Density 0.015%

    No Known Activations