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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or subjective opinions

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

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
     ok
    -0.41
     Dier
    -0.41
     wont
    -0.38
     ребё
    -0.37
     seper
    -0.36
    Whilst
    -0.36
     трёх
    -0.35
    Sólo
    -0.35
     wh
    -0.35
    POSITIVE LOGITS
    yntaxException
    0.62
     zijne
    0.59
     חיצוניים
    0.57
     BoxFit
    0.57
     mijne
    0.56
    ſelben
    0.56
     laſſen
    0.56
    ſchaft
    0.56
    apatalk
    0.55
     Geſch
    0.55
    Act Density 0.114%

    No Known Activations