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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal documentation and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Typography
    -0.20
     kind
    -0.17
    odos
    -0.15
    ufe
    -0.15
    icket
    -0.15
    ULLET
    -0.15
    amer
    -0.15
    iyon
    -0.14
    919
    -0.14
     beh
    -0.14
    POSITIVE LOGITS
     copy
    0.28
    Copy
    0.20
    copy
    0.20
     Copy
    0.19
     written
    0.18
     grace
    0.17
     maximum
    0.17
    _copy
    0.17
     COPY
    0.17
     estimate
    0.17
    Act Density 0.214%

    No Known Activations