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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to different versions or generalizations of a concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resa
    -0.16
     Braun
    -0.15
    ocht
    -0.15
     Wayback
    -0.15
    HS
    -0.15
    داد
    -0.14
    irus
    -0.14
    unday
    -0.14
    iming
    -0.14
    ob
    -0.13
    POSITIVE LOGITS
    (
    0.14
    agu
    0.14
    isson
    0.14
    437
    0.13
    atak
    0.13
     Rosenstein
    0.13
    ucci
    0.13
    罪
    0.13
     sorts
    0.13
    176
    0.13
    Act Density 0.099%

    No Known Activations