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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" followed by action verbs or other significant words

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

    Following "to" and a verb

    np_acts-logits-general · gemini-2.0-flash

    to followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.76
     <=",
    -0.70
    ModelBuilder
    -0.62
     surla
    -0.61
     صوتيه
    -0.58
    ніципа
    -0.57
    MigrationBuilder
    -0.57
     typelib
    -0.57
    下载附件
    -0.56
    цездатний
    -0.56
    POSITIVE LOGITS
    componentWill
    0.72
    componentDid
    0.65
    principalColumn
    0.54
     discuss
    0.52
     groet
    0.51
     vertellen
    0.50
     try
    0.49
    ngOnInit
    0.48
     fría
    0.47
     apologize
    0.47
    Act Density 0.132%

    No Known Activations