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

    Neuronpedia

    INDEX
    Explanations

    the intensifier "really" and its variations in emotional or evaluative contexts

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

    intensifiers or adverbs that suggest emphasis or significance

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

    really followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lamabad
    -0.65
    Chaos
    -0.58
    matchCondition
    -0.56
     depoz
    -0.55
    fois
    -0.54
     atheism
    -0.51
     hallucinations
    -0.51
    ctp
    -0.51
    -0.50
     Fais
    -0.50
    POSITIVE LOGITS
     nice
    0.67
    mergeFrom
    0.66
     cool
    0.65
    MessageOf
    0.64
     interesting
    0.62
    expandindo
    0.61
    MergeFrom
    0.61
     good
    0.60
     great
    0.59
     only
    0.59
    Act Density 0.019%

    No Known Activations