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

    Neuronpedia

    INDEX
    Explanations

    second-person descriptions of actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.73
    ector
    -0.69
    course
    -0.68
    SpaceEngineers
    -0.67
     theirs
    -0.66
    duty
    -0.62
    dimension
    -0.61
    odor
    -0.60
    OIL
    -0.60
    Mission
    -0.58
    POSITIVE LOGITS
    're
    1.49
    've
    1.21
     hear
    1.04
     arrive
    0.97
     compare
    0.94
     realize
    0.93
     contemplate
    0.92
     realise
    0.91
     combine
    0.89
     consider
    0.89
    Act Density 0.094%

    No Known Activations