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

    Neuronpedia

    INDEX
    Explanations

    references to shape and form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.55
     Reſ
    -0.51
     Diſ
    -0.47
    SEGUIR
    -0.45
     հղումներ
    -0.45
    StructEnd
    -0.44
     ſte
    -0.44
    toHaveBeenCalled
    -0.43
    ]');
    -0.43
     Houſe
    -0.43
    POSITIVE LOGITS
     shape
    0.98
     shapes
    0.85
    shape
    0.83
     shaped
    0.77
    shaped
    0.76
     Shape
    0.73
    shapes
    0.68
    Shaped
    0.66
     shaping
    0.66
     Shaped
    0.65
    Act Density 0.278%

    No Known Activations