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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enter
    -0.17
    ypy
    -0.16
    ioni
    -0.16
     दर
    -0.16
    rb
    -0.15
    lord
    -0.14
    exp
    -0.14
    rior
    -0.14
    ioxide
    -0.14
    orsche
    -0.14
    POSITIVE LOGITS
     among
    0.19
     amongst
    0.17
     such
    0.17
    ÐĴаж
    0.16
    ãĥ³ãĥĹ
    0.16
     biggest
    0.16
    ToMany
    0.15
     ÑģамÑĭÑħ
    0.15
     thing
    0.15
    Thing
    0.15
    Act Density 0.052%

    No Known Activations