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

    Neuronpedia

    INDEX
    Explanations

    negative contractions, particularly focusing on "don't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.15
    (CC
    -0.15
    apo
    -0.15
    ieber
    -0.14
    CDATA
    -0.14
    xec
    -0.14
    eenth
    -0.14
    oog
    -0.13
    ÙĪÙĦÙĪج
    -0.13
    oksen
    -0.13
    POSITIVE LOGITS
    اÙĦÙĩ
    0.16
    ocha
    0.16
    ATUS
    0.14
    edium
    0.14
    ief
    0.14
    æ
    0.14
    pq
    0.14
     Brake
    0.14
     deton
    0.13
    cke
    0.13
    Act Density 0.076%

    No Known Activations