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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or final outcomes

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

    Sentences starting with "Ultimately" or similar words

    np_acts-logits-general · gemini-2.0-flash

    ultimate conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.63
     initComponents
    -0.63
     heretofore
    -0.63
    IntoConstraints
    -0.61
     AssemblyCompany
    -0.59
     hitherto
    -0.59
    previously
    -0.58
     hâte
    -0.58
    примеча
    -0.58
     exciter
    -0.57
    POSITIVE LOGITS
     eventually
    0.88
     ultimately
    0.87
     Ultimately
    0.86
    Ultimately
    0.85
     Eventually
    0.83
    Eventually
    0.83
     uiteindelijk
    0.81
    eventually
    0.81
     eventual
    0.77
    ulti
    0.76
    Act Density 0.133%

    No Known Activations