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

    Neuronpedia

    INDEX
    Explanations

    terms indicating quality or evaluation related to decency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.17
    s
    -0.16
    ses
    -0.15
     Schwarz
    -0.15
    sit
    -0.15
    swer
    -0.15
    es
    -0.15
    is
    -0.14
    st
    -0.14
    !
    -0.14
    POSITIVE LOGITS
    -sized
    0.34
     sized
    0.32
     Sized
    0.29
    -size
    0.26
    -priced
    0.22
    -length
    0.19
     amount
    0.19
     decent
    0.18
     size
    0.18
     priced
    0.18
    Act Density 0.067%

    No Known Activations