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

    Neuronpedia

    INDEX
    Explanations

    imperative verb phrases prompting the reader to look at something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "look" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.67
    76561
    -0.62
    "},"
    -0.61
    CENT
    -0.58
     Unloaded
    -0.57
    ille
    -0.57
    RIC
    -0.56
    EStreamFrame
    -0.56
     RFC
    -0.54
    ItemImage
    -0.54
    POSITIVE LOGITS
     whence
    0.84
    ppe
    0.79
     how
    0.78
    who
    0.74
    what
    0.73
    outs
    0.72
    ed
    0.72
     closely
    0.71
    verning
    0.69
    !:
    0.69
    Act Density 0.030%

    No Known Activations