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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing products and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Folding
    -0.21
     folding
    -0.17
    zano
    -0.15
    _fold
    -0.15
    unfold
    -0.15
    Fold
    -0.15
    .VAL
    -0.14
    ROLL
    -0.14
    sono
    -0.14
    fold
    -0.14
    POSITIVE LOGITS
     polish
    0.29
     nail
    0.28
     Nail
    0.27
     pol
    0.25
     Polish
    0.23
     nails
    0.23
     manic
    0.22
    pol
    0.22
     opi
    0.22
     base
    0.21
    Act Density 0.005%

    No Known Activations