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

    Neuronpedia

    INDEX
    Explanations

    references to emotional complexity and depth in literary descriptions

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

    preceding adjectives

    np_acts-logits-general · gemini-2.0-flash

    descriptive eloquent virtuoso language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.71
    PRNewswire
    -0.67
     hype
    -0.63
    webElementXpaths
    -0.62
     standardize
    -0.58
    목
    -0.58
     ledit
    -0.57
     majorité
    -0.57
     stabilité
    -0.56
     Vordergrund
    -0.56
    POSITIVE LOGITS
    URLException
    0.74
     incis
    0.64
    Eloquent
    0.59
     poe
    0.57
     virtuoso
    0.57
     virtu
    0.56
     probing
    0.56
     arresting
    0.55
     distillation
    0.55
     begu
    0.54
    Act Density 0.301%

    No Known Activations