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

    Neuronpedia

    INDEX
    Explanations

    phrases related to shaping or influencing entities, such as culture or future outcomes

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

    shaping future or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AsyncTask
    -0.59
     nakalista
    -0.52
    Bakgrunnsstoff
    -0.51
     smtplib
    -0.47
    المشاركات
    -0.46
     <>",
    -0.46
    ErrorException
    -0.45
    Obrázky
    -0.44
    Tikang
    -0.44
     للمعارف
    -0.43
    POSITIVE LOGITS
     shaping
    1.01
     Shaping
    0.88
     shaped
    0.75
    haping
    0.73
     shape
    0.69
    SHAPE
    0.69
    塑造
    0.68
     molding
    0.63
     Shape
    0.62
    shape
    0.61
    Act Density 0.016%

    No Known Activations