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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and linking words that connect clauses or phrases

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

    "And" followed by indefinite/definite article

    np_acts-logits-general · gemini-2.0-flash

    followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anſ
    -0.62
    μφωνα
    -0.61
    utiliz
    -0.60
     ويكيميديا
    -0.59
    alyptus
    -0.59
     itſelf
    -0.59
    ſhip
    -0.59
    nefs
    -0.58
    իր
    -0.57
    ἶ
    -0.57
    POSITIVE LOGITS
    setVerticalGroup
    0.80
    basicConfig
    0.67
    StoryboardSegue
    0.60
    0.59
    ఔ
    0.58
    resave
    0.55
    __':
    0.55
    <bos>
    0.51
    ":[{
    0.51
     hence
    0.50
    Act Density 0.461%

    No Known Activations