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

    Neuronpedia

    INDEX
    Explanations

    references to degrees of murder or other legal classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sink
    -0.18
    è¨
    -0.15
    ész
    -0.15
    duk
    -0.14
     dirt
    -0.14
    νÏĦ
    -0.14
    ARTH
    -0.14
    ande
    -0.14
    itesse
    -0.14
     carpet
    -0.13
    POSITIVE LOGITS
    -degree
    0.42
     degree
    0.42
    degree
    0.37
     Degree
    0.34
    Degree
    0.28
    egree
    0.26
    .degree
    0.26
    _degree
    0.26
     grado
    0.24
     degrees
    0.22
    Act Density 0.005%

    No Known Activations