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

    Neuronpedia

    INDEX
    Explanations

    words related to connection or linkage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to connections and linking concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rit
    -0.79
    bis
    -0.76
    oÄŁ
    -0.72
    =-=-=-=-=-=-=-=-
    -0.69
    =-=-=-=-
    -0.69
    _-
    -0.69
    mpeg
    -0.67
    ached
    -0.67
    die
    -0.66
    cember
    -0.66
    POSITIVE LOGITS
     dots
    1.24
     disparate
    1.17
     together
    0.94
     them
    0.90
     apples
    0.86
     two
    0.81
     seamlessly
    0.81
     sexes
    0.80
     elements
    0.76
     oppos
    0.74
    Act Density 0.123%

    No Known Activations