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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions involving mixing, shaping, and frying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tying
    -0.85
     Tie
    -0.76
     tie
    -0.76
     string
    -0.75
    Tie
    -0.71
     tied
    -0.70
     strung
    -0.70
     knotted
    -0.69
     ties
    -0.69
     Chain
    -0.68
    POSITIVE LOGITS
     flattening
    0.90
     flatten
    0.90
     flattened
    0.85
     pressed
    0.80
     flat
    0.78
    flat
    0.77
     Flatten
    0.75
     Pressing
    0.75
    Flat
    0.75
     Flat
    0.74
    Act Density 0.830%

    No Known Activations