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

    Neuronpedia

    INDEX
    Explanations

    concepts related to learning and acquiring skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bor
    -0.17
    acos
    -0.16
     Stan
    -0.15
    Äįin
    -0.15
    uyá»ĩt
    -0.14
    &W
    -0.13
    /framework
    -0.13
    iÄį
    -0.13
    _ascii
    -0.13
    lou
    -0.13
    POSITIVE LOGITS
     Overall
    0.17
    edd
    0.15
     addCriterion
    0.15
    .sg
    0.15
    Overall
    0.15
    ¼åIJĪ
    0.14
     chosen
    0.14
     overall
    0.14
    seg
    0.14
    _fence
    0.14
    Act Density 0.031%

    No Known Activations