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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize limitation or exclusivity in context

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

    "Only" followed by a conditional word

    np_acts-logits-general · gemini-2.0-flash

    only if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.81
     Jefus
    -0.78
     myſelf
    -0.72
     Shakspeare
    -0.69
     Majefty
    -0.66
     Monfieur
    -0.66
     Psal
    -0.65
     himſelf
    -0.64
     Italijanski
    -0.63
     Octave
    -0.63
    POSITIVE LOGITS
     للاسماء
    0.69
     références
    0.59
     vagues
    0.51
    nskap
    0.49
    }}%
    0.48
     aquellos
    0.48
    })->
    0.47
     rarement
    0.46
     dager
    0.46
     refusé
    0.45
    Act Density 0.172%

    No Known Activations