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

    Neuronpedia

    INDEX
    Explanations

    phrases related to viewing or reviewing something

    oai_token-act-pair · gpt-3.5-turbo

    references to "sample" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    die
    -0.86
     destro
    -0.80
    ModLoader
    -0.80
    dies
    -0.79
    lesiastical
    -0.75
    verty
    -0.74
    iasis
    -0.71
    rid
    -0.71
    ledged
    -0.69
    lisher
    -0.68
    POSITIVE LOGITS
     sample
    0.85
     sizes
    0.84
     Sample
    0.80
    Grab
    0.79
     size
    0.78
     sampling
    0.78
    ographic
    0.71
     Size
    0.70
     samples
    0.69
    meal
    0.64
    Act Density 0.018%

    No Known Activations