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

    Neuronpedia

    INDEX
    Explanations

    words related to angles and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to angles and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raltar
    -0.82
    ingham
    -0.82
    士
    -0.79
    iability
    -0.78
    amn
    -0.76
    ledged
    -0.76
    culosis
    -0.76
    åŃIJ
    -0.75
    ains
    -0.73
    erd
    -0.72
    POSITIVE LOGITS
     brackets
    1.27
     angle
    1.12
     angles
    1.06
     bracket
    0.83
     jerk
    0.81
     thereto
    0.81
     angled
    0.75
    olate
    0.72
     Angle
    0.72
    yip
    0.71
    Act Density 0.035%

    No Known Activations