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

    Neuronpedia

    INDEX
    Explanations

    unique symbols and characters in the text, indicating specific formatting or markup elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yling
    -0.17
     Lamp
    -0.16
    .Restr
    -0.16
    ocy
    -0.15
    ozo
    -0.15
    lez
    -0.15
    oenix
    -0.14
    éĻ¢
    -0.14
    SystemService
    -0.14
    letic
    -0.14
    POSITIVE LOGITS
     Rot
    0.17
    rot
    0.16
    arga
    0.16
    ãĥ¥ãĥ¼
    0.15
    _rotation
    0.15
    abor
    0.15
    zag
    0.15
    affer
    0.15
    _rot
    0.15
     rotations
    0.15
    Act Density 0.005%

    No Known Activations