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

    Neuronpedia

    INDEX
    Explanations

    the word "over" used in different contexts, indicating repetition or duration

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

    over a quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.42
     ingår
    -0.41
    AnimationsModule
    -0.40
     ſche
    -0.40
     Conſ
    -0.39
     אותם
    -0.39
     seyn
    -0.36
    pexpr
    -0.35
    rollup
    -0.35
     Perſ
    -0.35
    POSITIVE LOGITS
    enumi
    0.59
    testens
    0.52
    complexContent
    0.51
     invokingState
    0.51
    󠁣
    0.48
    DURATION
    0.45
     <>",
    0.44
     AssemblyTitle
    0.44
    Duration
    0.43
     longer
    0.43
    Act Density 0.015%

    No Known Activations