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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" across various contexts

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

    followed by infinitive form "to" + verb

    np_acts-logits-general · gemini-2.0-flash

    infinitive verbs of action or observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.75
    出版年
    -0.66
     sqlSession
    -0.66
     pleaf
    -0.65
     elettrico
    -0.65
     avião
    -0.64
     femei
    -0.61
     Efq
    -0.61
    able
    -0.60
     gearbeitet
    -0.60
    POSITIVE LOGITS
     be
    1.16
     make
    0.91
     have
    0.90
     create
    0.85
     keep
    0.85
     do
    0.84
     become
    0.83
     develop
    0.83
     receive
    0.82
     get
    0.81
    Act Density 0.728%

    No Known Activations