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

    Neuronpedia

    INDEX
    Explanations

    repetitive sentence structures focusing on the word "so."

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

    Followed by a conjunction/pronoun

    np_acts-logits-general · gemini-2.0-flash

    so i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.69
     Efq
    -0.66
     Cæsar
    -0.64
    ſelves
    -0.63
     Shakspeare
    -0.61
     themſelves
    -0.60
     Diony
    -0.60
     himſelf
    -0.60
     Majefty
    -0.59
     Houſe
    -0.58
    POSITIVE LOGITS
     it
    1.15
     we
    1.09
     there
    1.07
     I
    0.92
     they
    0.86
     naturally
    0.82
     no
    0.80
     you
    0.77
     maybe
    0.77
     if
    0.76
    Act Density 0.071%

    No Known Activations