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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adding items to a list or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of adding something to a list or collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cki
    -0.65
    CHAT
    -0.62
    ults
    -0.61
    glers
    -0.61
    irection
    -0.61
    awn
    -0.60
    IPP
    -0.60
     miscar
    -0.59
    gency
    -0.59
    awei
    -0.59
    POSITIVE LOGITS
     compensate
    0.87
     bolster
    0.81
     orbit
    0.79
     complement
    0.74
     appease
    0.73
     shore
    0.73
     counteract
    0.69
     strengthen
    0.69
     clarify
    0.68
    orate
    0.67
    Act Density 0.092%

    No Known Activations