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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting within sentences

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

    Followed by a legal citation or transitional word

    np_acts-logits-general · gemini-2.0-flash

    sentence transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     there
    -0.82
     we
    -0.71
    there
    -0.70
     they
    -0.70
     دیگه
    -0.69
     you
    -0.69
     it
    -0.68
     I
    -0.65
     You
    -0.64
    they
    -0.64
    POSITIVE LOGITS
     Indeed
    1.07
    Indeed
    0.99
     Notably
    0.98
     Importantly
    0.98
     Specifically
    0.97
     Accordingly
    0.93
    Accordingly
    0.90
    Specifically
    0.89
     indeed
    0.89
     importantly
    0.86
    Act Density 0.847%

    No Known Activations