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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs related to movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "ran"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activation
    -0.72
    alty
    -0.72
    yet
    -0.71
    omical
    -0.71
    illusion
    -0.71
    olia
    -0.68
    ĨĴ
    -0.65
    rent
    -0.65
     Lauder
    -0.64
     maturity
    -0.63
    POSITIVE LOGITS
     Runner
    0.88
    swick
    0.87
     RUN
    0.86
     running
    0.77
    runner
    0.75
    running
    0.74
    Running
    0.73
    lasses
    0.73
    runners
    0.73
     runner
    0.73
    Act Density 0.015%

    No Known Activations