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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific term or topic related to a place or entity

    oai_token-act-pair · gpt-3.5-turbo

    the name "Sp" followed by various identifiers or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.81
    ãĥĥãĥĪ
    -0.80
    ĸļ
    -0.76
    ģĸ
    -0.70
     Incarnation
    -0.70
    stery
    -0.69
    cised
    -0.68
    WAYS
    -0.67
    DragonMagazine
    -0.65
    hof
    -0.65
    POSITIVE LOGITS
    itt
    1.15
    atial
    1.11
    aghetti
    1.10
    okes
    1.10
    ooky
    1.07
    itting
    1.06
    encer
    1.05
    atter
    1.04
    ork
    1.04
    rit
    1.02
    Act Density 0.013%

    No Known Activations