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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant amounts or proportions of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubl
    -0.15
    .AutoScaleMode
    -0.15
    ÑĢÑĸÑĪ
    -0.14
    burg
    -0.14
    agli
    -0.14
    raquo
    -0.14
    éal
    -0.14
    ål
    -0.14
    enburg
    -0.13
    oš
    -0.13
    POSITIVE LOGITS
     of
    0.46
     part
    0.35
     của
    0.32
     portion
    0.32
     parte
    0.27
    of
    0.25
    à¸Ĥà¸Ńà¸ĩ
    0.25
    portion
    0.25
     ÏĦηÏĤ
    0.24
     portions
    0.23
    Act Density 0.054%

    No Known Activations