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

    Neuronpedia

    INDEX
    Explanations

    references to sequential steps or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uges
    -0.17
    obby
    -0.16
    lid
    -0.16
    line
    -0.15
    er
    -0.15
    laps
    -0.15
    rine
    -0.14
    iding
    -0.14
    /up
    -0.14
    eness
    -0.14
    POSITIVE LOGITS
    éª
    0.26
    wise
    0.25
    -by
    0.22
    .Step
    0.20
    han
    0.20
    father
    0.20
    dad
    0.20
    é©
    0.20
    (step
    0.19
     Step
    0.18
    Act Density 0.034%

    No Known Activations