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

    Neuronpedia

    INDEX
    Explanations

    terms related to toxicity in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trás
    -0.57
     Generous
    -0.57
     depri
    -0.56
     flink
    -0.56
     kveld
    -0.55
    venido
    -0.54
    aphthalene
    -0.54
    nanoTime
    -0.53
    harusnya
    -0.53
    CLUSIVE
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.76
    ViewFeatures
    0.64
    toxic
    0.62
     toxic
    0.62
     Yel
    0.61
     upside
    0.60
    <tbody>
    0.59
    poison
    0.59
    Ecotoxicity
    0.58
    хьтан
    0.58
    Act Density 2.250%

    No Known Activations