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

    Neuronpedia

    INDEX
    Explanations

    instances of historical or significant firsts in various contexts

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

    "First" followed by an infinitive

    np_acts-logits-general · gemini-2.0-flash

    to + verb + achievement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -0.81
     Administrativna
    -0.80
     betweenstory
    -0.76
     Audiodateien
    -0.73
    DockStyle
    -0.72
    parsedMessage
    -0.70
    IntoConstraints
    -0.69
     itſelf
    -0.69
    Personendaten
    -0.68
     estekak
    -0.67
    POSITIVE LOGITS
     ever
    0.82
     truly
    0.69
     réellement
    0.66
     überhaupt
    0.64
     véritable
    0.63
     explicitly
    0.61
     consistently
    0.60
     directly
    0.60
     complete
    0.56
     vraiment
    0.55
    Act Density 0.243%

    No Known Activations