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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating the sequence or order of actions

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

    sequential steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.33
     bezpečnost
    -0.32
     convient
    -0.31
     henvisninger
    -0.31
    berdayakan
    -0.30
    (()=>
    -0.30
     صوتيه
    -0.30
    stateMutability
    -0.29
     sû
    -0.29
     levens
    -0.29
    POSITIVE LOGITS
    rungsseite
    0.70
     have
    0.70
     had
    0.68
    MLLoader
    0.65
     didn
    0.61
    unzel
    0.59
     couldn
    0.59
     gave
    0.59
     ſind
    0.59
     missed
    0.58
    Act Density 0.070%

    No Known Activations