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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adding something to an existing entity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the action of adding something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miscar
    -0.74
    cffffcc
    -0.72
    ults
    -0.71
    Champ
    -0.67
    rowth
    -0.65
    ;;;;;;;;
    -0.62
    zeb
    -0.62
    tions
    -0.62
    ATIONS
    -0.61
    BUS
    -0.61
    POSITIVE LOGITS
     bolster
    0.91
    pload
    0.83
     complement
    0.82
     shore
    0.76
     enhance
    0.76
     compensate
    0.74
     fill
    0.73
     accompany
    0.69
    adies
    0.68
     replace
    0.66
    Act Density 0.142%

    No Known Activations