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

    Neuronpedia

    INDEX
    Explanations

    references to angles and positioning in relation to physical objects or equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohana
    -0.16
    presso
    -0.16
    dou
    -0.16
     edin
    -0.15
    ingham
    -0.15
     Knot
    -0.15
    zon
    -0.15
    stretch
    -0.14
    ilha
    -0.14
    elop
    -0.14
    POSITIVE LOGITS
     angle
    0.49
     angles
    0.45
    angle
    0.40
     Angle
    0.39
    è§Ĵ
    0.36
    -angle
    0.36
     angels
    0.36
    Angle
    0.33
    angles
    0.33
     tilt
    0.32
    Act Density 0.116%

    No Known Activations