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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting alternative ideas or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    expressions questioning the status quo or proposing alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.87
    ItemTracker
    -0.69
    photo
    -0.68
    Runner
    -0.68
    Ö¼
    -0.63
     Auditor
    -0.63
     Bulgar
    -0.62
    cedented
    -0.62
    utch
    -0.61
    ollen
    -0.61
    POSITIVE LOGITS
     indulge
    0.94
    ?!
    0.93
     emulate
    0.86
    ?]
    0.83
     unleash
    0.83
     recreate
    0.83
     incorporate
    0.81
     let
    0.81
    ...?
    0.80
     intervene
    0.80
    Act Density 0.049%

    No Known Activations