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

    Neuronpedia

    INDEX
    Explanations

    concerns related to toxins and their impact on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     empt
    -0.14
    tran
    -0.14
    ivor
    -0.14
    ży
    -0.14
     Kak
    -0.13
    inode
    -0.13
     empty
    -0.13
    ovel
    -0.13
     Overflow
    -0.13
    eur
    -0.13
    POSITIVE LOGITS
     exposure
    0.83
     Exposure
    0.75
     exposures
    0.68
     exposed
    0.66
     expos
    0.61
     expose
    0.60
    Exposed
    0.57
     exposing
    0.56
    ex
    0.55
     exposes
    0.52
    Act Density 0.145%

    No Known Activations