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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases starting with "if."

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

    "If" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    conditional decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.61
     bileklik
    -0.56
     eventdata
    -0.55
     godk
    -0.54
     solcher
    -0.54
     behandeling
    -0.53
     astfel
    -0.51
     testamento
    -0.50
     døde
    -0.50
     başına
    -0.49
    POSITIVE LOGITS
     unsure
    0.73
    ,'\
    0.69
     none
    0.68
     contemplating
    0.68
    WireFormatLite
    0.67
     haven
    0.66
    )");
    0.65
     looking
    0.62
    ]));
    0.61
     experiencing
    0.60
    Act Density 0.102%

    No Known Activations