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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expression or inner dialogue

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

    Follows periods in dialogue or text

    np_acts-logits-general · gemini-2.0-flash

    code or mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stället
    -0.57
     économies
    -0.56
     paſſ
    -0.52
    CppMethod
    -0.52
     enfans
    -0.51
     ſhe
    -0.51
     ſur
    -0.50
    forRoot
    -0.50
    ]=>
    -0.50
     ſch
    -0.50
    POSITIVE LOGITS
     swears
    0.68
     ©️
    0.64
    Personendaten
    0.62
     shoved
    0.61
     colouring
    0.59
     swore
    0.57
    دانشنامهٔ
    0.56
    oOo
    0.56
     tumblr
    0.55
     Tumblr
    0.55
    Act Density 0.222%

    No Known Activations