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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that involve conjunctions and comparative structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    epam
    -0.16
    ystone
    -0.14
    uthor
    -0.14
    drv
    -0.14
    lesi
    -0.14
    rame
    -0.14
    loat
    -0.14
    ekim
    -0.14
    ingga
    -0.14
    RAINT
    -0.14
    POSITIVE LOGITS
    hari
    0.17
     indeed
    0.16
    Viewport
    0.16
     alike
    0.15
    teÅŁ
    0.14
     jedn
    0.14
    ced
    0.14
    éĶ
    0.13
    \Db
    0.13
    опаÑģ
    0.13
    Act Density 0.336%

    No Known Activations