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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and structures that indicate reasoning or an argument's progression

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

    that start sentences or clauses

    np_acts-logits-general · gemini-2.0-flash

    sentence transition words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illetve
    -0.51
     valamint
    -0.50
     alebo
    -0.50
     antaranya
    -0.48
    }`,
    -0.47
     （
    -0.47
    trui
    -0.46
    herself
    -0.46
     mutta
    -0.45
     }},
    -0.45
    POSITIVE LOGITS
     there
    1.23
     they
    1.11
     it
    1.07
     we
    1.06
    there
    0.95
     if
    0.85
     الدولى
    0.78
     when
    0.78
     these
    0.78
     you
    0.77
    Act Density 0.452%

    No Known Activations