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

    Neuronpedia

    INDEX
    Explanations

    references to cones and cone-shaped objects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    siella
    -0.73
    esserung
    -0.69
    noch
    -0.67
     bain
    -0.67
     walla
    -0.67
    mby
    -0.66
     Winslow
    -0.66
    Wallis
    -0.66
    ثيق
    -0.66
     Picchu
    -0.65
    POSITIVE LOGITS
     Cone
    1.51
    Cone
    1.51
     cone
    1.41
     cones
    1.38
    cone
    1.04
     conical
    0.91
    msgSender
    0.86
    cones
    0.85
    锥
    0.80
     wands
    0.75
    Act Density 0.002%

    No Known Activations