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

    Neuronpedia

    INDEX
    Explanations

    phrases related to environmental warnings and advisories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewood
    -0.15
    pcl
    -0.15
    enger
    -0.15
     sleep
    -0.14
    idth
    -0.14
    gard
    -0.14
    usan
    -0.14
    eck
    -0.14
     Cir
    -0.14
    _NOP
    -0.14
    POSITIVE LOGITS
     unhealthy
    0.20
    ople
    0.17
     Chow
    0.17
    otts
    0.16
    elm
    0.16
     ÐŁÐ»Ð¾
    0.15
    olk
    0.15
     turb
    0.15
    .lazy
    0.15
     Heal
    0.15
    Act Density 0.010%

    No Known Activations