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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" followed by another word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging observation or scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "}],"
    -0.77
    ially
    -0.69
    dar
    -0.69
    etter
    -0.68
    alli
    -0.65
    ilib
    -0.65
    venge
    -0.65
     PsyNet
    -0.64
    sheet
    -0.63
    etermined
    -0.62
    POSITIVE LOGITS
     examples
    0.79
     Skies
    0.78
     example
    0.74
     Example
    0.74
     hypot
    0.72
     FIG
    0.72
    asm
    0.72
     Compare
    0.72
     analogy
    0.70
    example
    0.68
    Act Density 0.106%

    No Known Activations