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

    Neuronpedia

    INDEX
    Explanations

    references to scientific citations and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hank
    -0.17
    elt
    -0.15
    este
    -0.15
    391
    -0.15
    emos
    -0.15
    nid
    -0.14
    eward
    -0.14
    481
    -0.14
    841
    -0.13
    示
    -0.13
    POSITIVE LOGITS
     Dice
    0.15
    ÑĨеÑĢ
    0.15
    .SetToolTip
    0.15
    hire
    0.14
    MinMax
    0.14
    à¥įथन
    0.14
    croll
    0.14
    .github
    0.14
     arrang
    0.13
    umblr
    0.13
    Act Density 0.029%

    No Known Activations