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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ision
    -0.17
    ales
    -0.16
    keit
    -0.16
    ngine
    -0.15
     Ill
    -0.15
    Cached
    -0.15
    _eng
    -0.15
    ãģ§ãģĤ
    -0.15
    omp
    -0.14
    ضÙĬ
    -0.14
    POSITIVE LOGITS
    strom
    0.17
    ward
    0.16
     finally
    0.15
    856
    0.15
    IDGE
    0.15
    essa
    0.15
     later
    0.14
    __[
    0.14
    605
    0.14
     Ferr
    0.14
    Act Density 0.089%

    No Known Activations