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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating organizational actions or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igon
    -0.14
    λικά
    -0.14
    stit
    -0.14
    ught
    -0.14
    bidden
    -0.14
    ufe
    -0.13
    ras
    -0.13
    IFT
    -0.13
    515
    -0.13
    776
    -0.13
    POSITIVE LOGITS
     separate
    0.24
     series
    0.24
     mechanism
    0.23
     seperate
    0.20
     number
    0.19
     variety
    0.18
     dedicated
    0.18
     serie
    0.18
     suite
    0.18
     list
    0.18
    Act Density 0.326%

    No Known Activations