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

    Neuronpedia

    INDEX
    Explanations

    legal terminology related to liability and claims

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

    Follows "whether" or "<start_of_turn>user"

    np_acts-logits-general · gemini-2.0-flash

    whether in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.64
     utafitiHapana
    -0.59
    zeptember
    -0.50
     ब्रेकडाउन
    -0.49
    fjspx
    -0.44
     المعيارى
    -0.43
    SharedCtor
    -0.41
     برانيه
    -0.41
     informée
    -0.40
    應
    -0.39
    POSITIVE LOGITS
     οπο
    0.58
     ANY
    0.56
    任何
    0.54
     Cualquier
    0.54
     cualquier
    0.52
     ANYTHING
    0.48
     any
    0.47
     quelconque
    0.47
    complexContent
    0.46
     qualsiasi
    0.45
    Act Density 0.270%

    No Known Activations