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

    Neuronpedia

    INDEX
    Explanations

    references to specific scholars or their works, particularly relating to mathematical estimates or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astery
    -0.16
    aida
    -0.16
    rice
    -0.16
    naments
    -0.15
    irk
    -0.15
    .sleep
    -0.15
    rax
    -0.15
    umont
    -0.14
    DonaldTrump
    -0.14
    rite
    -0.14
    POSITIVE LOGITS
    opor
    0.21
    eo
    0.18
    omy
    0.18
    ensibly
    0.17
     eo
    0.17
    EO
    0.16
    agma
    0.15
    rog
    0.15
    rogen
    0.15
    ernen
    0.15
    Act Density 0.006%

    No Known Activations