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

    Neuronpedia

    INDEX
    Explanations

    instructions or recommendations to prevent undesirable outcomes

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

    "Avoid" and subsequent actions/objects

    np_acts-logits-general · gemini-2.0-flash

    avoiding specific problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.66
     ferdig
    -0.65
     vertes
    -0.62
    Datuak
    -0.62
     publiques
    -0.59
     extérieures
    -0.58
    orithmic
    -0.57
     fær
    -0.56
     dieux
    -0.55
     réguli
    -0.55
    POSITIVE LOGITS
     Avoid
    0.75
    noinspection
    0.74
    Avoid
    0.73
     unnecessary
    0.72
     AVOID
    0.71
     avoid
    0.69
     avoiding
    0.68
     pitfalls
    0.68
    avoid
    0.68
     defaultstate
    0.66
    Act Density 0.124%

    No Known Activations