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

    Neuronpedia

    INDEX
    Explanations

    occurrences of class identifiers and specific class-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wunused
    -0.16
    itchen
    -0.15
    anagan
    -0.15
    enha
    -0.14
    ibar
    -0.14
    çµµ
    -0.14
    nung
    -0.14
    çĦ
    -0.14
    .FontStyle
    -0.14
    abay
    -0.14
    POSITIVE LOGITS
    ç´ł
    0.19
    mdi
    0.15
    elon
    0.14
    HELL
    0.14
    ylon
    0.14
    èĢIJ
    0.14
    891
    0.14
    سط
    0.14
     bro
    0.14
    531
    0.13
    Act Density 0.002%

    No Known Activations