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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intent, particularly those beginning with "to."

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

    "To" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    To introducing purpose or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.80
    thâu
    -0.66
    AutoScale
    -0.63
    èrement
    -0.57
     pylint
    -0.56
    GenerationType
    -0.56
     {})
    -0.53
    فرد
    -0.52
    Nazionale
    -0.52
    ⓧ
    -0.52
    POSITIVE LOGITS
     To
    0.78
     Чтобы
    0.76
    To
    0.73
     estimés
    0.64
    Чтобы
    0.64
     avoid
    0.61
     recap
    0.60
     summarize
    0.58
     illustrate
    0.58
    éviter
    0.57
    Act Density 0.093%

    No Known Activations