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

    Neuronpedia

    INDEX
    Explanations

    references to specific publications and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cl
    -0.16
    Figure
    -0.15
     Fal
    -0.14
    çIJ
    -0.14
     Mae
    -0.13
    ufe
    -0.13
    emark
    -0.13
    legation
    -0.13
     Figure
    -0.13
    addOn
    -0.13
    POSITIVE LOGITS
    åł
    0.15
    elpers
    0.14
     SUBSTITUTE
    0.14
    ourd
    0.14
    RAY
    0.14
    Traits
    0.14
    ivos
    0.13
    //{{
    0.13
    ARGET
    0.13
    rawer
    0.13
    Act Density 0.046%

    No Known Activations