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

    Neuronpedia

    INDEX
    Explanations

    adverbs that denote a degree of emotional response or surprise

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

    intense adverbs describing qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esModule
    -0.54
     برانيه
    -0.49
     laiton
    -0.45
     Escolar
    -0.44
    horabuena
    -0.42
     چیست
    -0.40
    agisse
    -0.40
    Bibliograf
    -0.40
     adquis
    -0.40
     defaultstate
    -0.39
    POSITIVE LOGITS
     pleasantly
    1.49
     delightfully
    0.98
     deliciously
    0.86
     surprisingly
    0.74
     mildly
    0.71
     surprised
    0.68
     wonderfully
    0.68
    comfortably
    0.65
     noticeably
    0.61
     Surprisingly
    0.61
    Act Density 0.002%

    No Known Activations