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

    Neuronpedia

    INDEX
    Explanations

    references to lead roles or lead positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minded
    -0.15
    isations
    -0.15
    unan
    -0.15
    fik
    -0.15
    acker
    -0.14
    aal
    -0.14
    ackbar
    -0.14
    ohn
    -0.14
     Leading
    -0.14
    _AMD
    -0.14
    POSITIVE LOGITS
    ed
    0.21
    ings
    0.19
    ÂŃing
    0.18
     poisoning
    0.18
    lined
    0.18
    edBy
    0.17
     singer
    0.17
    ship
    0.17
    off
    0.17
    feb
    0.17
    Act Density 0.010%

    No Known Activations