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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating effort, striving, and agency

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

    followed by "to" indicating effort or striving

    np_acts-logits-general · gemini-2.0-flash

    striving for a goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.66
    Referencie
    -0.63
     kasarigan
    -0.62
    abestanden
    -0.62
     insuffisamment
    -0.60
    __(/*!
    -0.59
    :✨
    -0.58
    Infof
    -0.54
     Roskov
    -0.53
    MergeFrom
    -0.52
    POSITIVE LOGITS
     to
    0.82
     чтобы
    0.74
     щоб
    0.60
     أجل
    0.60
     để
    0.59
     affinch
    0.58
     againſt
    0.56
     desesper
    0.56
     Чтобы
    0.56
     initComponents
    0.56
    Act Density 0.284%

    No Known Activations