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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating relative size or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essian
    -0.17
    lest
    -0.16
    laces
    -0.15
    ulu
    -0.14
     Halk
    -0.14
    uitka
    -0.14
    thalm
    -0.14
    Å¡el
    -0.14
    quine
    -0.14
    ewise
    -0.14
    POSITIVE LOGITS
     times
    0.27
    fold
    0.25
     fold
    0.25
     normal
    0.22
     Fold
    0.20
    Fold
    0.20
     (!
    0.20
    -fold
    0.20
    times
    0.19
     greater
    0.19
    Act Density 0.035%

    No Known Activations