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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "over," often in relation to estimations or measurements

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

    prefixed 'over-'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.54
    примеча
    -0.54
    <bos>
    -0.54
    NUMX
    -0.53
    Alike
    -0.53
    tagHelperRunner
    -0.51
    scenes
    -0.49
     насељу
    -0.49
    uki
    -0.49
     Szen
    -0.48
    POSITIVE LOGITS
     over
    0.87
     Over
    0.81
    Over
    0.73
     ओवर
    0.72
     OVER
    0.71
    over
    0.68
     overly
    0.68
    オーバー
    0.63
    OVER
    0.62
     Overs
    0.61
    Act Density 0.037%

    No Known Activations