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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with law enforcement and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Assembly
    -0.70
     Breakfast
    -0.68
     surn
    -0.65
     Islands
    -0.65
    Scroll
    -0.63
    onics
    -0.63
    bian
    -0.63
    anka
    -0.63
     Cree
    -0.62
    ukemia
    -0.61
    POSITIVE LOGITS
     unconsciously
    1.16
     subconscious
    1.14
     implicitly
    0.96
     passively
    0.94
     instinctively
    0.90
     thereby
    0.89
     infer
    0.87
     knowing
    0.85
     subtly
    0.85
     perce
    0.85
    Act Density 1.146%

    No Known Activations