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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.15
    ži
    -0.14
    -library
    -0.14
    KIT
    -0.14
    (mut
    -0.13
     миÑģÑĤ
    -0.13
    unde
    -0.13
     Jaune
    -0.13
    istik
    -0.13
    uja
    -0.13
    POSITIVE LOGITS
     teams
    0.14
     PhD
    0.13
     ug
    0.13
     professor
    0.13
     pros
    0.13
    ãĥ³ãĥĨ
    0.13
     et
    0.13
     Stranger
    0.12
     Department
    0.12
    woke
    0.12
    Act Density 0.062%

    No Known Activations