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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantity or proportion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poffible
    -0.65
     enged
    -0.57
    :+:
    -0.57
    kész
    -0.57
    corporated
    -0.55
    щении
    -0.54
    ultuous
    -0.54
    redients
    -0.52
     acost
    -0.52
     anytime
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.81
    FormTagHelper
    0.77
    MLLoader
    0.72
     MessageBoxIcon
    0.66
    lossians
    0.66
    ImageContext
    0.65
    IsContent
    0.65
     تانيه
    0.64
     OnInit
    0.64
    tocin
    0.62
    Act Density 0.231%

    No Known Activations