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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, decisions, and descriptions of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and action-oriented statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.78
    è¦ļéĨĴ
    -0.69
    javascript
    -0.68
    ],"
    -0.66
     guiActiveUnfocused
    -0.65
    "âĢ¦
    -0.62
    inatory
    -0.61
    present
    -0.61
    "—
    -0.61
    enable
    -0.60
    POSITIVE LOGITS
    cknowled
    0.87
    cknow
    0.87
    resy
    0.78
    itialized
    0.66
    oret
    0.65
     Bye
    0.61
    ONSORED
    0.60
     Clause
    0.59
    verning
    0.59
     typo
    0.58
    Act Density 0.667%

    No Known Activations