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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or formal occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯
    -0.15
    st
    -0.14
    hes
    -0.14
    APE
    -0.14
     distr
    -0.14
     Eins
    -0.14
    rum
    -0.14
     ape
    -0.13
    api
    -0.13
     insol
    -0.13
    POSITIVE LOGITS
    engin
    0.18
    izoph
    0.17
    Wunused
    0.16
    liš
    0.15
    mtx
    0.15
    rug
    0.15
    ordinal
    0.15
    ανδ
    0.15
    Sphere
    0.15
    ären
    0.14
    Act Density 0.001%

    No Known Activations