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

    Neuronpedia

    INDEX
    Explanations

    casual conversational phrases and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Layout
    -0.16
    éri
    -0.16
    Ñľ
    -0.16
    ozem
    -0.16
    fü
    -0.15
    rine
    -0.15
    uges
    -0.15
    Ø®ÙĪاÙĨ
    -0.15
    EMON
    -0.15
    zo
    -0.15
    POSITIVE LOGITS
    pher
    0.17
    863
    0.16
    xx
    0.16
    ieten
    0.16
    SizeMode
    0.15
    son
    0.15
    ãĤ·ãĤ¢
    0.14
     Jackson
    0.14
     Fraser
    0.14
     th
    0.14
    Act Density 0.116%

    No Known Activations