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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to artwork and its presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Runtime
    -0.15
    èĤ¥
    -0.14
    梯
    -0.14
     æ¹
    -0.14
     Fet
    -0.14
    cup
    -0.14
     εμÏĢ
    -0.13
    ÑĢазд
    -0.13
     Aires
    -0.13
    glyph
    -0.13
    POSITIVE LOGITS
     frame
    0.45
     frames
    0.40
     Frame
    0.39
    Frame
    0.38
     framing
    0.36
     Frames
    0.36
    -frame
    0.34
    frame
    0.34
     FRAME
    0.33
     Fram
    0.33
    Act Density 0.029%

    No Known Activations