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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate fairness or appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.17
    maal
    -0.16
     Beled
    -0.15
    roduction
    -0.15
    endale
    -0.14
    omer
    -0.14
    ngen
    -0.14
    (Source
    -0.14
    ाà¤Ĭ
    -0.14
    ache
    -0.14
    POSITIVE LOGITS
    ably
    0.24
    -sized
    0.24
    ately
    0.21
     sized
    0.20
    hof
    0.18
    -priced
    0.17
     decent
    0.17
     fair
    0.16
     Sized
    0.16
    οι
    0.15
    Act Density 0.066%

    No Known Activations