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

    Neuronpedia

    INDEX
    Explanations

    references to feedback or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skill
    -0.15
    545
    -0.15
     Dou
    -0.14
    orre
    -0.14
    ottom
    -0.14
    odiac
    -0.13
     Banking
    -0.13
    ãĥ¼ãĥĦ
    -0.13
    voj
    -0.13
    han
    -0.13
    POSITIVE LOGITS
    /gtest
    0.17
    /disable
    0.16
    sembly
    0.14
    MeasureSpec
    0.14
    -Identifier
    0.14
     ÄĮer
    0.14
    avage
    0.14
     ãĢ
    0.14
    mps
    0.13
    .DeepEqual
    0.13
    Act Density 0.005%

    No Known Activations