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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating contrast or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.81
     myſelf
    -0.80
     sandero
    -0.78
     Efq
    -0.76
    ſelves
    -0.75
     Majefty
    -0.74
     houſe
    -0.72
     Kości
    -0.67
     المعيارى
    -0.66
     Monfieur
    -0.65
    POSITIVE LOGITS
     it
    1.01
     if
    0.80
     we
    0.77
     I
    0.76
     the
    0.72
     there
    0.71
     they
    0.65
     you
    0.61
     he
    0.61
     although
    0.60
    Act Density 0.348%

    No Known Activations