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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and decisions made by an individual

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the verb "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.81
    ONSORED
    -0.75
    ItemTracker
    -0.69
    ESA
    -0.68
    raltar
    -0.67
    isu
    -0.65
    é¾įå¥ij士
    -0.64
    uably
    -0.60
    Leader
    -0.59
    USS
    -0.59
    POSITIVE LOGITS
    zed
    0.93
    pez
    0.92
     wonders
    0.91
    vet
    0.88
     everything
    0.87
     NOT
    0.85
    omsday
    0.84
     homework
    0.82
     not
    0.82
    oms
    0.81
    Act Density 0.098%

    No Known Activations