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

    Neuronpedia

    INDEX
    Explanations

    references to system design and evaluation methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     everywhere
    -0.15
     finally
    -0.14
    OLON
    -0.13
     Everywhere
    -0.13
    uture
    -0.13
    isoft
    -0.12
     ЧаÑģ
    -0.12
    AGMA
    -0.12
     anywhere
    -0.12
    nemonic
    -0.12
    POSITIVE LOGITS
     Existing
    0.25
     Traditional
    0.24
    Existing
    0.22
     Classic
    0.22
     Convention
    0.22
    Traditional
    0.21
     Classical
    0.21
     State
    0.21
     Inspired
    0.20
    Classic
    0.20
    Act Density 0.057%

    No Known Activations