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

    Neuronpedia

    INDEX
    Explanations

    assertions and perspectives that convey certainty or caution in various contexts

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

    intensifiers and qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.82
     imagui
    -0.77
    majánló
    -0.77
    ſicht
    -0.76
     autorytatywna
    -0.75
    <unused79>
    -0.73
    <unused16>
    -0.72
    <unused28>
    -0.72
    <unused3>
    -0.72
    <pad>
    -0.72
    POSITIVE LOGITS
     that
    0.50
     
    0.48
     the
    0.45
     (
    0.44
    The
    0.44
    метров
    0.44
      
    0.43
     The
    0.43
    1
    0.42
    2
    0.41
    Act Density 0.034%

    No Known Activations