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

    Neuronpedia

    INDEX
    Explanations

    statements that challenge common misconceptions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    increments
    -0.18
    996
    -0.16
    æľĽ
    -0.15
    rax
    -0.15
    shan
    -0.15
    yna
    -0.14
     Mature
    -0.14
    pped
    -0.14
    ging
    -0.14
     princ
    -0.14
    POSITIVE LOGITS
    acter
    0.15
    chos
    0.15
    lok
    0.15
    kü
    0.14
     ren
    0.14
     pau
    0.14
    æį
    0.14
    erval
    0.14
    ":↵
    0.13
    fram
    0.13
    Act Density 0.487%

    No Known Activations