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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "shape" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.19
    eday
    -0.18
    self
    -0.17
    lland
    -0.16
    borg
    -0.15
    lando
    -0.15
    leri
    -0.15
    esse
    -0.15
    rome
    -0.15
     McCabe
    -0.14
    POSITIVE LOGITS
    (shape
    0.24
     Shape
    0.24
     shape
    0.23
     shaped
    0.22
    less
    0.21
    .shape
    0.21
     shapes
    0.21
    lessness
    0.20
    shape
    0.20
     Morph
    0.18
    Act Density 0.017%

    No Known Activations