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

    Neuronpedia

    INDEX
    Explanations

    chemical compound names related to health risks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the chemical BPA and its associated risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.84
    tie
    -0.84
    line
    -0.78
    lers
    -0.73
    space
    -0.72
    iques
    -0.70
    naire
    -0.69
    link
    -0.67
    bar
    -0.67
    bolt
    -0.66
    POSITIVE LOGITS
    WN
    0.98
    veyard
    0.96
    BLE
    0.91
    GE
    0.91
    WD
    0.90
    INT
    0.88
    odcast
    0.87
    ussy
    0.86
    BILITY
    0.83
    IRED
    0.83
    Act Density 0.014%

    No Known Activations