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

    Neuronpedia

    INDEX
    Explanations

    phrases involving actions performed or decisions made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rep
    -0.60
    herry
    -0.59
     Metatron
    -0.57
     Kle
    -0.57
     impe
    -0.56
     Patri
    -0.55
     Fool
    -0.54
     Kru
    -0.54
     Ner
    -0.54
    ocide
    -0.53
    POSITIVE LOGITS
    abouts
    0.78
     during
    0.69
    rentices
    0.65
    uggle
    0.64
    */(
    0.64
    ãĥ¼ãĤ¯
    0.64
     beforehand
    0.63
    alian
    0.62
    ulus
    0.61
    anas
    0.60
    Act Density 0.281%

    No Known Activations