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

    Neuronpedia

    INDEX
    Explanations

    code that updates or modifies numeric values or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uling
    -0.15
    stoup
    -0.15
    rien
    -0.15
    erry
    -0.15
    roker
    -0.15
    rell
    -0.14
    éĢļãĤĬ
    -0.14
    ollen
    -0.14
    rient
    -0.14
    iveau
    -0.14
    POSITIVE LOGITS
    eya
    0.16
    ped
    0.15
    IDO
    0.14
     pin
    0.14
     belly
    0.14
    ansson
    0.13
    ti
    0.13
     knull
    0.13
    pin
    0.13
    æī
    0.13
    Act Density 0.015%

    No Known Activations