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

    Neuronpedia

    INDEX
    Explanations

    architectural and design concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.74
    CLASSIFIED
    -0.72
     EFF
    -0.72
     FORM
    -0.69
     Habit
    -0.68
     SAN
    -0.68
     Publishers
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
     USA
    -0.65
     Austral
    -0.65
    POSITIVE LOGITS
    rust
    0.88
    outed
    0.87
    uple
    0.86
    ucer
    0.85
    act
    0.83
    ropy
    0.83
    ink
    0.82
    vered
    0.82
    asp
    0.82
    umeric
    0.81
    Act Density 0.122%

    No Known Activations