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

    Neuronpedia

    INDEX
    Explanations

    references to time, location, and direction within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    needle
    -0.15
    owi
    -0.15
    xito
    -0.15
    åĩ¡
    -0.14
    hlas
    -0.14
    illisecond
    -0.14
    olation
    -0.14
    reamble
    -0.14
    heritance
    -0.13
    Configurer
    -0.13
    POSITIVE LOGITS
    ope
    0.15
    601
    0.15
    uela
    0.15
    ture
    0.15
    rtle
    0.14
    ulk
    0.14
    RELATED
    0.14
    äh
    0.14
    istic
    0.14
     Sü
    0.13
    Act Density 0.083%

    No Known Activations