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

    Neuronpedia

    INDEX
    Explanations

    references to the letter 'H' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asp
    -0.18
    ornings
    -0.15
    itr
    -0.15
     Pole
    -0.15
     progression
    -0.14
    unn
    -0.14
    orum
    -0.14
    аÑĢÑĮ
    -0.14
    quier
    -0.14
    ows
    -0.14
    POSITIVE LOGITS
    amed
    0.23
    él
    0.22
    iltr
    0.22
    ilda
    0.22
    anne
    0.22
    erve
    0.21
    rips
    0.21
    ajar
    0.20
    iliary
    0.20
    annel
    0.20
    Act Density 0.025%

    No Known Activations