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

    Neuronpedia

    INDEX
    Explanations

    specific objects or items among a collection

    oai_token-act-pair · gpt-3.5-turbo

    specific items and their characteristics or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.67
    Angelo
    -0.66
     observes
    -0.66
     contends
    -0.61
    Beg
    -0.58
    Incre
    -0.56
     concurrent
    -0.56
     participates
    -0.55
     believes
    -0.54
     observing
    -0.54
    POSITIVE LOGITS
     aren
    1.67
     ARE
    1.47
     are
    1.43
     weren
    1.40
     suck
    1.33
     belong
    1.31
     seem
    1.30
     contain
    1.28
     deserve
    1.25
     dont
    1.25
    Act Density 0.446%

    No Known Activations