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

    Neuronpedia

    INDEX
    Explanations

    Prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings and positional data in a list context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.65
     exerted
    -0.61
    ivities
    -0.61
    oubted
    -0.60
     ampl
    -0.60
    oyle
    -0.60
    ighters
    -0.59
    ressive
    -0.59
    ÃĽ
    -0.58
    ĸļ
    -0.57
    POSITIVE LOGITS
     ninth
    1.45
     seventh
    1.44
     sixth
    1.42
     eighth
    1.41
     fifth
    1.34
     fourth
    1.34
     tenth
    1.19
     third
    1.19
     second
    1.11
     Nos
    1.10
    Act Density 0.225%

    No Known Activations