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

    Neuronpedia

    INDEX
    Explanations

    words related to angles within a visual context

    oai_token-act-pair · gpt-3.5-turbo

    references to angles in visual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raltar
    -0.86
    weet
    -0.84
    ingham
    -0.83
    accompan
    -0.81
    culosis
    -0.80
    essee
    -0.78
    ledged
    -0.77
    æĸ¹
    -0.76
    åŃIJ
    -0.76
    ains
    -0.75
    POSITIVE LOGITS
     brackets
    1.14
     angle
    1.04
     angles
    0.97
     Angle
    0.83
     jerk
    0.83
     thereto
    0.76
    yip
    0.75
     latitude
    0.73
     angled
    0.70
     lens
    0.70
    Act Density 0.032%

    No Known Activations