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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different individuals having experience working under specific people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a context of performance evaluation or supervision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iterranean
    -0.76
    ument
    -0.68
    bernatorial
    -0.65
    ILLE
    -0.62
     Edison
    -0.61
    `
    -0.60
    auga
    -0.60
    0000000000000000
    -0.60
     Warsaw
    -0.57
    Minecraft
    -0.57
    POSITIVE LOGITS
    pins
    1.08
    dogs
    1.06
    neath
    1.04
    lining
    1.02
    whelming
    1.01
    cutting
    0.96
    graduate
    0.95
    whel
    0.94
    lined
    0.94
    cuts
    0.94
    Act Density 0.047%

    No Known Activations