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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement and direction

    oai_token-act-pair · gpt-3.5-turbo

    actions and movements related to physical direction or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ician
    -0.75
    cause
    -0.72
    iest
    -0.68
    swick
    -0.67
    eries
    -0.67
    orde
    -0.66
    official
    -0.65
    lords
    -0.65
    Ñı
    -0.63
    esome
    -0.63
    POSITIVE LOGITS
     scrolling
    0.98
    ttle
    0.89
     piv
    0.88
     clock
    0.88
     gears
    0.86
     downward
    0.85
     mute
    0.82
     gaze
    0.82
     dial
    0.81
     clocks
    0.81
    Act Density 0.320%

    No Known Activations