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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and authors' names in research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.18
    beth
    -0.16
    .mb
    -0.15
     embod
    -0.14
    tring
    -0.14
    /Sub
    -0.14
    odore
    -0.14
    apı
    -0.13
    bach
    -0.13
    /Set
    -0.13
    POSITIVE LOGITS
    mainwindow
    0.15
    incip
    0.14
    posit
    0.14
    žil
    0.13
    zl
    0.13
     Chick
    0.13
    nger
    0.12
     --------------------------------------------------------------------------↵
    0.12
    nop
    0.12
    丰
    0.12
    Act Density 0.025%

    No Known Activations