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

    Neuronpedia

    INDEX
    Explanations

    phrases that express personal perception and belief systems

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

    Follows personal pronouns or names

    np_acts-logits-general · gemini-2.0-flash

    how you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Teilnahme
    -0.57
     noires
    -0.54
     diferenças
    -0.50
     }}"></
    -0.48
     différences
    -0.46
     publicados
    -0.46
     illustrationer
    -0.45
     électroniques
    -0.45
    differences
    -0.44
    location
    -0.43
    POSITIVE LOGITS
     behave
    1.10
     behaves
    1.04
     handled
    1.04
     behaved
    1.00
     behaving
    0.93
     approach
    0.91
     approached
    0.91
     worded
    0.90
     handle
    0.89
     approaching
    0.88
    Act Density 0.260%

    No Known Activations