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

    Neuronpedia

    INDEX
    Explanations

    quoted statements that express opinions or reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wers
    -0.20
    lover
    -0.18
    æĺĩ
    -0.15
    )((((
    -0.15
     Alone
    -0.15
    ours
    -0.15
    جب
    -0.14
    ãĤ§
    -0.14
     Grove
    -0.14
    سر
    -0.14
    POSITIVE LOGITS
    .BLL
    0.17
    currentColor
    0.15
    artz
    0.14
    ãĥ«ãĤ¯
    0.14
    ivalent
    0.14
    iek
    0.14
    átor
    0.14
    XT
    0.13
    810
    0.13
    mán
    0.13
    Act Density 0.009%

    No Known Activations