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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs indicating transfer of status or recognition

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

    Preceding punctuation (, \)

    np_acts-logits-general · gemini-2.0-flash

    confer/given followed by noun/number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </b>
    -0.64
      
    -0.57
    </i>
    -0.56
    numerusform
    -0.50
    –
    -0.50
       
    -0.50
    lapsingToolbar
    -0.48
    <eos>
    -0.48
    ↵↵
    -0.48
    ↵
    -0.47
    POSITIVE LOGITS
     незавершена
    0.89
     ſind
    0.87
     ་་
    0.85
    raisemb
    0.85
    etcode
    0.84
    __":
    0.83
    BagConstraints
    0.82
     vooz
    0.81
     パンチラ
    0.81
     erſten
    0.80
    Act Density 2.636%

    No Known Activations