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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "is" indicating definitions or statements of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    this
    -0.18
     this
    -0.18
    enberg
    -0.17
    ovo
    -0.16
     there
    -0.15
     shock
    -0.15
    ubar
    -0.15
     these
    -0.15
    amp
    -0.14
    t
    -0.13
    POSITIVE LOGITS
    /th
    0.15
    OperationException
    0.15
    hait
    0.15
    AtA
    0.14
    Latch
    0.14
    abis
    0.14
    .FontStyle
    0.14
    agate
    0.14
    -tm
    0.14
    morgan
    0.14
    Act Density 0.075%

    No Known Activations