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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distance or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant discrepancy from an ideal or expected state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.78
    ysis
    -0.72
    ptive
    -0.67
    piracy
    -0.66
    ulus
    -0.66
    ription
    -0.65
    icks
    -0.64
    ellation
    -0.63
    iliary
    -0.63
     Peel
    -0.62
    POSITIVE LOGITS
     enough
    1.07
    thing
    0.96
    fetched
    0.92
    enough
    0.91
    med
    0.87
     Enough
    0.84
    entimes
    0.83
    zx
    0.78
    ranging
    0.74
    itud
    0.73
    Act Density 0.021%

    No Known Activations