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

    Neuronpedia

    INDEX
    Explanations

    phrases describing different types or categories

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    romeda
    -0.81
     Rings
    -0.81
    umbai
    -0.79
    姫
    -0.78
    pload
    -0.76
    olulu
    -0.76
     Bots
    -0.75
     destro
    -0.75
    nuts
    -0.74
    iae
    -0.73
    POSITIVE LOGITS
    face
    1.49
    faces
    1.44
    etter
    1.19
    etting
    1.15
    casting
    1.07
    ahead
    1.02
    cast
    0.89
    classes
    0.89
    alias
    0.84
    typ
    0.83
    Act Density 10.631%

    No Known Activations