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

    Neuronpedia

    INDEX
    Explanations

    emotional descriptors and expressions of disappointment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pose
    -0.15
    ìłľ
    -0.15
     trib
    -0.15
    odd
    -0.15
     Mos
    -0.14
    ington
    -0.14
     Sad
    -0.14
    NESS
    -0.14
    ignet
    -0.14
    utsch
    -0.14
    POSITIVE LOGITS
    ικ
    0.15
    shan
    0.15
    _lite
    0.15
    adow
    0.15
    tright
    0.14
    lli
    0.14
    vý
    0.14
    ãĤ«ãĥ«
    0.14
    .ActionListener
    0.14
    OutOfBounds
    0.14
    Act Density 1.666%

    No Known Activations