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

    Neuronpedia

    INDEX
    Explanations

    trademarks and branded terms

    oai_token-act-pair · gpt-3.5-turbo

    trademarks or brand identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -1.00
    furt
    -0.76
    vernment
    -0.75
    */(
    -0.74
    bats
    -0.73
    shall
    -0.73
    byss
    -0.70
    vier
    -0.69
    batch
    -0.68
    selage
    -0.68
    POSITIVE LOGITS
    NT
    0.94
    asters
    0.94
    obile
    0.92
    GT
    0.82
    RC
    0.82
    astics
    0.81
    TI
    0.80
    GP
    0.79
    asks
    0.78
    astic
    0.78
    Act Density 0.026%

    No Known Activations