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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something that seems too good, bad, intense, or large to believe or manage

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of something being "too good to be true."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flix
    -0.80
    ihad
    -0.71
    ãĥĨ
    -0.68
    eneg
    -0.68
    chwitz
    -0.67
    issance
    -0.65
    ses
    -0.65
    charged
    -0.65
     largeDownload
    -0.64
     uncanny
    -0.64
    POSITIVE LOGITS
     contemplate
    1.01
     bother
    0.91
     warrant
    0.85
     tolerate
    0.84
     handle
    0.83
     swallow
    0.81
    inventoryQuantity
    0.81
     merit
    0.79
     feas
    0.79
     ignore
    0.77
    Act Density 0.091%

    No Known Activations