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

    Neuronpedia

    INDEX
    Explanations

    terms related to toxicity, particularly in a biological or chemical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    toxicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.66
     للمعارف
    -0.60
     لينك
    -0.59
    ſelben
    -0.58
    KommentareTeilen
    -0.57
     purpoſe
    -0.57
     laſſen
    -0.57
    ſicht
    -0.57
     témoig
    -0.55
    AsNil
    -0.55
    POSITIVE LOGITS
    toxicity
    1.73
     toxicity
    0.75
    toxic
    0.57
     shit
    0.52
     toxic
    0.52
     motherfucker
    0.52
     Toxicity
    0.52
     TOXIC
    0.51
    Toxicity
    0.51
     fuck
    0.50
    Act Density 0.001%

    No Known Activations