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

    Neuronpedia

    INDEX
    Explanations

    instances of user interaction prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.18
    ils
    -0.16
    aniel
    -0.15
     XO
    -0.15
    ynes
    -0.15
    anas
    -0.15
    otto
    -0.15
    raci
    -0.15
     Wake
    -0.14
    olut
    -0.14
    POSITIVE LOGITS
    ety
    0.20
    .echo
    0.19
    tiv
    0.18
    íĴĪ
    0.17
    loquent
    0.17
    hole
    0.16
    asso
    0.16
     Robertson
    0.16
    à¸ģ
    0.15
    mousedown
    0.15
    Act Density 0.026%

    No Known Activations