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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" with varying emphasis

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

    to followed by action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affatto
    -0.36
     folhas
    -0.35
    hoeddwyd
    -0.34
    Choice
    -0.34
     hagy
    -0.33
     figliu
    -0.33
    

    -0.33
     Lay
    -0.33
    <bos>
    -0.33
     sobą
    -0.32
    POSITIVE LOGITS
    findpost
    0.72
    addCriterion
    0.58
    mybatisplus
    0.50
    ImageContext
    0.49
    OGND
    0.49
    suri
    0.48
    weeper
    0.47
    новништво
    0.47
     désolés
    0.45
     nahilalakip
    0.45
    Act Density 0.053%

    No Known Activations