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

    Neuronpedia

    INDEX
    Explanations

    terms related to quality and classification in documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /she
    -0.15
     ï
    -0.15
     certain
    -0.15
    sel
    -0.15
     lately
    -0.14
    ses
    -0.14
     various
    -0.14
     particular
    -0.14
    eres
    -0.14
    /or
    -0.14
    POSITIVE LOGITS
    aneously
    0.24
    /current
    0.23
    /original
    0.20
    -issue
    0.20
    mente
    0.20
    -purpose
    0.18
    ively
    0.18
    -use
    0.16
    ;y
    0.16
    -lived
    0.16
    Act Density 0.782%

    No Known Activations