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

    Neuronpedia

    INDEX
    Explanations

    past and present tense forms of the verb "to be" in various contexts

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

    "is" or "are" followed by "not"

    np_acts-logits-general · gemini-2.0-flash

    is not, is often, is very

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baterie
    -0.62
     normalization
    -0.58
    these
    -0.56
     decrees
    -0.55
     Underlying
    -0.54
     amounts
    -0.53
     linearity
    -0.51
    IBOutlet
    -0.51
     cuffs
    -0.51
     alluminio
    -0.51
    POSITIVE LOGITS
     not
    1.05
     able
    1.00
     worth
    0.95
     still
    0.90
     actually
    0.90
     always
    0.87
     seen
    0.85
     likely
    0.85
     held
    0.83
    "):
    0.83
    Act Density 2.369%

    No Known Activations