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

    Neuronpedia

    INDEX
    Explanations

    expressions of inequality or comparisons not equal to a specific value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hop
    -0.18
    chedulers
    -0.17
    ãģĨãģ¡
    -0.15
    stone
    -0.14
    hen
    -0.14
    ìĽĥ
    -0.14
    ÙĦت
    -0.14
    zeug
    -0.13
    isle
    -0.13
    holder
    -0.13
    POSITIVE LOGITS
    null
    0.17
    nil
    0.15
     necessarily
    0.15
    arro
    0.15
    iced
    0.14
    Ìĥ
    0.14
    ideo
    0.14
    abez
    0.14
    tal
    0.14
    uesday
    0.14
    Act Density 0.023%

    No Known Activations