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

    Neuronpedia

    INDEX
    Explanations

    conjunctions used to connect phrases or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ermann
    -0.15
    ered
    -0.14
    cio
    -0.14
     Roths
    -0.14
     pits
    -0.14
    .Cmd
    -0.13
     runnable
    -0.13
    Enlarge
    -0.13
    _categorical
    -0.13
    _rq
    -0.13
    POSITIVE LOGITS
    kers
    0.18
     alike
    0.15
     Jenner
    0.15
     Md
    0.14
    zers
    0.14
     Marvin
    0.14
    hive
    0.14
    ImageData
    0.13
    alian
    0.13
    ally
    0.13
    Act Density 0.177%

    No Known Activations