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

    Neuronpedia

    INDEX
    Explanations

    phrases related to receiving feedback or attention from a community or audience

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases associated with receiving or gaining attention and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alone
    -0.72
    arta
    -0.70
    agate
    -0.67
    -|
    -0.65
     Dise
    -0.65
    velt
    -0.65
    ooters
    -0.64
    rue
    -0.62
    ared
    -0.61
    ta
    -0.61
    POSITIVE LOGITS
     rave
    1.30
     praise
    1.23
     widespread
    1.22
     acclaim
    1.17
     considerable
    1.14
     accol
    1.14
     notoriety
    1.14
     headlines
    1.04
     attention
    1.03
     condemnation
    1.03
    Act Density 0.133%

    No Known Activations