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

    Neuronpedia

    INDEX
    Explanations

    references to sliding actions or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.18
    éĨĴ
    -0.17
    κÏģι
    -0.16
    ossal
    -0.16
    veau
    -0.15
    ész
    -0.14
    .MM
    -0.14
    ensors
    -0.14
    uky
    -0.14
    agen
    -0.14
    POSITIVE LOGITS
    y
    0.19
    .echo
    0.16
    gota
    0.15
    &p
    0.14
    ades
    0.14
    ý
    0.14
    ars
    0.14
    atch
    0.14
    pond
    0.14
    ilm
    0.13
    Act Density 0.007%

    No Known Activations