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

    Neuronpedia

    INDEX
    Explanations

    textual cues indicating dialogue or conversation

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

    Followed by punctuation or a capital letter

    np_acts-logits-general · gemini-2.0-flash

    speaker identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.69
    SharedDtor
    -0.64
    featureID
    -0.64
     لينك
    -0.64
    contentLoaded
    -0.63
    SourceChecksum
    -0.63
     autorytatywna
    -0.62
     myſelf
    -0.61
    ]")]
    -0.61
     NDEBUG
    -0.61
    POSITIVE LOGITS
    ❋
    0.63
      
    0.55
     interviewer
    0.50
    RAE
    0.50
    :
    0.49
    szön
    0.47
          
    0.45
    endpush
    0.45
       
    0.45
     desorption
    0.43
    Act Density 0.389%

    No Known Activations