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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and notation typically used in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.16
    joy
    -0.15
     cáºŃn
    -0.15
    elere
    -0.14
    exter
    -0.14
    EMPTY
    -0.14
    lor
    -0.14
    edn
    -0.14
    omatic
    -0.14
    etto
    -0.14
    POSITIVE LOGITS
    owitz
    0.17
    altung
    0.14
     toy
    0.14
    adan
    0.14
    etik
    0.14
    adin
    0.14
    602
    0.14
    MS
    0.14
    ombat
    0.14
    rix
    0.13
    Act Density 0.014%

    No Known Activations