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

    Neuronpedia

    INDEX
    Explanations

    expressions of praise and positive assessment

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

    great job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreInfinity
    -0.40
     dimiliki
    -0.38
     âgées
    -0.37
     personnalisée
    -0.37
     cromado
    -0.36
     Lebens
    -0.35
     vilka
    -0.35
     Bürgermeister
    -0.35
    tså
    -0.34
     äldre
    -0.34
    POSITIVE LOGITS
     Doing
    0.56
    Doing
    0.53
     Done
    0.53
     done
    0.52
     doing
    0.51
    دانشنامهٔ
    0.49
    __':
    0.48
     DONE
    0.48
     Performed
    0.48
     ModelExpression
    0.47
    Act Density 0.006%

    No Known Activations