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

    Neuronpedia

    INDEX
    Explanations

    emphatic expressions and phrases indicating regret or emphasis on the importance of context

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

    ATLAS not hiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.50
    lorette
    -0.48
     crochê
    -0.47
     ||=
    -0.46
    berdayakan
    -0.46
    AsUp
    -0.46
    newArrayList
    -0.46
     ModelRenderer
    -0.44
    دانشنامهٔ
    -0.44
     außerdem
    -0.44
    POSITIVE LOGITS
     trattano
    0.46
     Unburied
    0.46
     endblock
    0.43
    outSlope
    0.42
     transfieras
    0.40
    styleType
    0.40
     kasarigan
    0.39
     koti
    0.38
    braucher
    0.37
    :✨
    0.36
    Act Density 0.050%

    No Known Activations