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

    Neuronpedia

    INDEX
    Explanations

    sequence of brackets and array-like structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vell
    -0.18
    ages
    -0.15
    omit
    -0.15
    ottage
    -0.14
     Bris
    -0.14
    .Initialize
    -0.14
    orr
    -0.14
    elas
    -0.14
    forgettable
    -0.14
     sever
    -0.14
    POSITIVE LOGITS
    ERVED
    0.16
    enco
    0.15
    агаÑĤо
    0.15
    æĴ
    0.15
    tics
    0.15
    imed
    0.15
    rtle
    0.14
    bens
    0.14
    ivan
    0.14
    adow
    0.14
    Act Density 0.002%

    No Known Activations