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

    Neuronpedia

    INDEX
    Explanations

    mentions of various data types and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ry
    -0.23
    min
    -0.19
    ary
    -0.19
    rod
    -0.18
    Enum
    -0.18
    ue
    -0.17
    ri
    -0.17
    rc
    -0.17
    ly
    -0.17
    nt
    -0.16
    POSITIVE LOGITS
    æħĭ
    0.19
    ahead
    0.17
    kits
    0.16
    asily
    0.15
    chk
    0.15
    gli
    0.15
    face
    0.15
    ICAL
    0.14
    ologically
    0.14
    chai
    0.14
    Act Density 0.094%

    No Known Activations