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

    Neuronpedia

    INDEX
    Explanations

    specific types of measurable outcomes or results in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ottes
    -0.14
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.14
    entiful
    -0.13
    ennon
    -0.12
    unbind
    -0.12
     elsewhere
    -0.12
    uckland
    -0.12
    emey
    -0.12
     SUCH
    -0.11
     '".
    -0.11
    POSITIVE LOGITS
     each
    1.41
    each
    1.22
     Each
    1.09
     EACH
    1.09
    Each
    1.05
    .each
    0.90
    _each
    0.90
     кажд
    0.90
     cada
    0.87
     chaque
    0.84
    Act Density 0.739%

    No Known Activations