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

    Neuronpedia

    INDEX
    Explanations

    phrases related to corroborating or supporting statements with evidence or proof

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to supporting or validating assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.94
    Ô
    -0.72
    apo
    -0.72
    owan
    -0.70
    erves
    -0.68
    NetMessage
    -0.67
    _>
    -0.66
    bell
    -0.65
    eston
    -0.65
    kie
    -0.64
    POSITIVE LOGITS
    dates
    0.73
    IFT
    0.72
    olicy
    0.68
    packs
    0.67
    dating
    0.66
     STATS
    0.66
    stock
    0.64
    dt
    0.64
     DATA
    0.64
    grading
    0.63
    Act Density 0.025%

    No Known Activations