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

    Neuronpedia

    INDEX
    Explanations

    references or citations indicated by the term "Ref."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or subjects in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.76
    ahime
    -0.72
    daq
    -0.70
     pockets
    -0.66
    ################
    -0.66
    matically
    -0.66
     Horses
    -0.63
     whiff
    -0.63
     atmosphere
    -0.63
     oper
    -0.62
    POSITIVE LOGITS
    eree
    1.47
    lection
    1.39
    lections
    1.39
    riger
    1.33
    erred
    1.27
    erences
    1.25
    lected
    1.25
    lect
    1.23
    erential
    1.23
    eren
    1.22
    Act Density 0.030%

    No Known Activations