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

    Neuronpedia

    INDEX
    Explanations

    angles and spatial relationships in text

    oai_token-act-pair · gpt-3.5-turbo

    references to angles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raltar
    -0.86
    士
    -0.83
    weet
    -0.82
    ingham
    -0.82
    essee
    -0.82
    ledged
    -0.82
    ains
    -0.80
    amn
    -0.79
    ularity
    -0.78
    ifying
    -0.78
    POSITIVE LOGITS
     brackets
    1.15
     angle
    1.08
     angles
    0.98
     jerk
    0.86
     thereto
    0.82
     Angle
    0.71
     barb
    0.71
     elevation
    0.70
     flare
    0.67
     ratios
    0.67
    Act Density 0.021%

    No Known Activations