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

    Neuronpedia

    INDEX
    Explanations

    dates or numerical ranges formatted in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    pharmaceutical dosage information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iane
    -0.72
    egu
    -0.69
    iple
    -0.69
    oller
    -0.68
    ysis
    -0.67
    ©¶æ
    -0.65
     redes
    -0.64
    zzy
    -0.62
    ravity
    -0.62
    ijn
    -0.61
    POSITIVE LOGITS
    _>
    0.85
    batch
    0.80
    micro
    0.76
    bury
    0.75
    âĪĴ
    0.75
    facing
    0.75
    ––
    0.73
    PsyNetMessage
    0.72
    advertising
    0.70
    Pg
    0.70
    Act Density 0.019%

    No Known Activations