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

    Neuronpedia

    INDEX
    Explanations

    measurements in millimeters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dimensions or measurements in millimeters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.92
    hire
    -0.84
    irie
    -0.81
    bable
    -0.81
    lez
    -0.79
    comes
    -0.78
    raltar
    -0.77
    hran
    -0.76
    prom
    -0.76
    spell
    -0.75
    POSITIVE LOGITS
     diameter
    1.09
     aperture
    0.78
    itted
    0.77
     spacing
    0.76
    ORPG
    0.74
     offset
    0.74
     thickness
    0.74
     diam
    0.74
     wrench
    0.72
     thick
    0.70
    Act Density 0.010%

    No Known Activations