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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.15
    atrix
    -0.15
    osas
    -0.15
    ither
    -0.15
    inis
    -0.14
     surrounds
    -0.14
    ãģ¤ãģij
    -0.14
    avel
    -0.14
    mrt
    -0.14
    133
    -0.13
    POSITIVE LOGITS
    shiv
    0.15
     Baker
    0.14
    emek
    0.14
    ë²Į
    0.14
    zing
    0.14
    ůr
    0.14
    zsche
    0.14
    aker
    0.14
    ãĥ©ãĥ¼
    0.14
    ,readonly
    0.13
    Act Density 0.064%

    No Known Activations