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

    Neuronpedia

    INDEX
    Explanations

    uncommon symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    highly frequent or notable characters or shows from popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    getic
    -0.81
     mathemat
    -0.81
    izzard
    -0.76
    bris
    -0.76
    asus
    -0.74
     juggling
    -0.72
     notor
    -0.71
     fortun
    -0.71
     misunder
    -0.71
     princ
    -0.68
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    1.08
    \/
    1.04
    ¯
    0.97
    ±
    0.91
    º
    0.90
    !--
    0.89
    âĶĢâĶĢ
    0.87
    """
    0.87
    ¯¯
    0.86
    -+
    0.85
    Act Density 0.050%

    No Known Activations