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

    Neuronpedia

    INDEX
    Explanations

    references or mentions of specific terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    daq
    -0.72
    ESE
    -0.71
    amaru
    -0.65
     whiff
    -0.63
    \\\\\\\\
    -0.63
     Kinnikuman
    -0.63
    ################
    -0.62
    ECD
    -0.62
    DAQ
    -0.62
    adena
    -0.62
    POSITIVE LOGITS
    eree
    1.22
    inement
    1.10
    erences
    1.09
    inished
    1.04
    ractive
    1.04
    lection
    1.02
    actor
    1.02
    erred
    1.01
    erential
    0.98
    riger
    0.96
    Act Density 0.006%

    No Known Activations