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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating hypothetical or conditional situations

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

    The token "would" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    would followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.79
     Lipa
    -0.78
     Schrader
    -0.73
     Percival
    -0.70
     Conci
    -0.69
    Aspiration
    -0.68
     Adair
    -0.68
     swans
    -0.67
     énergé
    -0.67
     GSC
    -0.66
    POSITIVE LOGITS
    ULD
    1.00
    _^
    0.89
     WOULD
    0.85
     Would
    0.83
    iosync
    0.83
     would
    0.83
    >>>>>>>>
    0.82
    /−
    0.80
     be
    0.80
    letal
    0.79
    Act Density 0.161%

    No Known Activations