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

    Neuronpedia

    INDEX
    Explanations

    key terms related to incidents and evaluations of fairness in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.16
     Heb
    -0.15
    urette
    -0.15
    ÑĢод
    -0.14
     thous
    -0.14
    surname
    -0.14
    mlin
    -0.14
    036
    -0.14
    .Modules
    -0.13
    sik
    -0.13
    POSITIVE LOGITS
    eco
    0.16
    iners
    0.15
    èĸ
    0.14
    .TabStop
    0.14
     doc
    0.14
    ẩm
    0.14
    cher
    0.14
    è±
    0.13
     Blond
    0.13
    acles
    0.13
    Act Density 0.012%

    No Known Activations