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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locating or determining the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons and their associated information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cknow
    -0.83
    etheless
    -0.76
     unfocusedRange
    -0.64
    Reviewer
    -0.64
    cknowled
    -0.62
     Invalid
    -0.61
     refusing
    -0.60
     overriding
    -0.60
     unable
    -0.60
     denying
    -0.59
    POSITIVE LOGITS
     originated
    1.28
     resides
    1.21
     occurs
    1.06
     occurred
    0.98
     resided
    0.98
     originate
    0.97
     came
    0.95
     origin
    0.95
     meets
    0.92
     arose
    0.91
    Act Density 0.212%

    No Known Activations