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

    Neuronpedia

    INDEX
    Explanations

    phrases that express hope and assurance for accountability or improvement

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

    "So that..."

    np_acts-logits-general · gemini-2.0-flash

    prediction that clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     koska
    -0.66
     ponieważ
    -0.64
    IBarButtonItem
    -0.64
     kvůli
    -0.61
     karena
    -0.60
     SINCE
    -0.59
     BECAUSE
    -0.59
     poichè
    -0.57
     mivel
    -0.57
     yüzden
    -0.56
    POSITIVE LOGITS
     opportunities
    0.66
     together
    0.64
     hopefully
    0.63
     whatever
    0.63
     chances
    0.61
    Together
    0.59
     future
    0.59
     everyone
    0.58
    hopefully
    0.57
     nantinya
    0.56
    Act Density 0.194%

    No Known Activations