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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction with services and their effectiveness

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

    Positive adjectives and interjections

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives, staff descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }();
    -0.59
    (',');
    -0.58
     ddelweddau
    -0.57
    protoimpl
    -0.56
    ictwa
    -0.56
    alisation
    -0.56
    ganu
    -0.55
    styleType
    -0.55
    TagMode
    -0.55
     consultancy
    -0.54
    POSITIVE LOGITS
     friendly
    0.75
     Friendly
    0.73
     cleanest
    0.72
    Friendly
    0.71
     staff
    0.70
     ramah
    0.69
     always
    0.68
     ALWAYS
    0.68
    Always
    0.66
     awesome
    0.66
    Act Density 0.028%

    No Known Activations