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

    Neuronpedia

    INDEX
    Explanations

    various references to types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ezier
    -0.15
     instrument
    -0.15
     Hind
    -0.14
    905
    -0.14
    veis
    -0.14
    SEQ
    -0.14
     Instrument
    -0.14
    abil
    -0.13
    holm
    -0.13
    stell
    -0.13
    POSITIVE LOGITS
    ologne
    0.16
    ger
    0.16
    OCKET
    0.15
    uctor
    0.15
    entionPolicy
    0.15
    istar
    0.15
    DIRECTORY
    0.14
    oÄį
    0.14
    NAL
    0.14
    unately
    0.14
    Act Density 0.017%

    No Known Activations