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

    Neuronpedia

    INDEX
    Explanations

    instructions or warnings related to the use of medication

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

    Following negative advice or warnings

    np_acts-logits-general · gemini-2.0-flash

    avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.72
    RectangleBorder
    -0.66
    AddTagHelper
    -0.62
    anskje
    -0.61
    elemField
    -0.61
    دانشنامهٔ
    -0.61
     autorytatywna
    -0.61
     protoimpl
    -0.60
    ///</
    -0.59
     nakalista
    -0.58
    POSITIVE LOGITS
     avoid
    1.44
     Avoid
    1.44
    Avoid
    1.38
    avoid
    1.23
     AVOID
    1.17
     avoids
    1.11
     NEVER
    1.07
     avoiding
    1.06
     éviter
    1.05
     evitar
    1.04
    Act Density 0.286%

    No Known Activations