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

    Neuronpedia

    INDEX
    Explanations

    specific words and phrases related to arguments, reasoning, and the presentation of evidence in a legal or analytical context

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

    Follows proper nouns or titles

    np_acts-logits-general · gemini-2.0-flash

    tricks she learned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auroit
    -1.00
     feroit
    -0.96
     avoient
    -0.92
     étoient
    -0.92
     Theſe
    -0.90
     Efq
    -0.88
     pouvoit
    -0.87
     étoit
    -0.87
     Cæsar
    -0.85
     ſeveral
    -0.84
    POSITIVE LOGITS
     Mr
    0.64
    HasAnnotation
    0.61
     Smith
    0.56
     the
    0.54
     Ben
    0.54
    derung
    0.53
     
    0.52
    Distribuzione
    0.51
    }{*}{
    0.51
     Mel
    0.50
    Act Density 1.433%

    No Known Activations