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

    Neuronpedia

    INDEX
    Explanations

    references to software versioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    w
    -0.17
    udden
    -0.16
    itter
    -0.15
    ilk
    -0.15
    iswa
    -0.15
    ps
    -0.14
    wards
    -0.14
    ONO
    -0.14
    ICI
    -0.14
    ice
    -0.14
    POSITIVE LOGITS
    ing
    0.26
    åı·
    0.19
    neutral
    0.19
    èĻŁ
    0.19
     neutral
    0.19
    ning
    0.18
    stamp
    0.18
    _major
    0.18
    .major
    0.18
    ed
    0.17
    Act Density 0.015%

    No Known Activations