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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or dashes that indicate pauses or breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åķ
    -0.17
    fé
    -0.16
    ellido
    -0.14
    acman
    -0.14
    xec
    -0.14
    ingga
    -0.14
    auc
    -0.14
    eed
    -0.14
    oth
    -0.13
    ilder
    -0.13
    POSITIVE LOGITS
    sdale
    0.15
    oret
    0.15
    lich
    0.15
     equals
    0.15
     both
    0.14
     rare
    0.14
    NX
    0.14
    uni
    0.13
    both
    0.13
    ãĥ¼ãĥ
    0.13
    Act Density 0.127%

    No Known Activations