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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or research

    oai_token-act-pair · gpt-3.5-turbo

    references to academic studies or research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passing
    -0.65
     veto
    -0.62
    Calling
    -0.61
    âĹ¼
    -0.60
    Introduced
    -0.60
    OPA
    -0.59
    ENCY
    -0.58
     Saying
    -0.58
     rotting
    -0.58
     chanting
    -0.58
    POSITIVE LOGITS
     examined
    1.26
     examines
    1.22
     investigates
    1.19
     investigated
    1.16
     analyzed
    1.16
     analysed
    1.15
     surveyed
    1.10
     explored
    1.09
     tested
    1.08
     consisted
    1.07
    Act Density 0.110%

    No Known Activations