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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or considerations

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

    "Might" or "may" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    might be followed by adjective/participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evidently
    -1.01
     presumably
    -0.98
     apparently
    -0.93
    presumably
    -0.92
     obviously
    -0.90
     basically
    -0.86
     usually
    -0.86
     Presumably
    -0.84
    apparently
    -0.84
     Evidently
    -0.83
    POSITIVE LOGITS
     jopa
    1.00
    anskje
    0.99
     algún
    0.93
     depending
    0.93
     someday
    0.89
    depending
    0.83
     some
    0.80
     sogar
    0.78
     might
    0.77
     zelfs
    0.75
    Act Density 0.588%

    No Known Activations