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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and conjunctions used to indicate relationships between ideas in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.71
     Houſe
    -0.69
    herself
    -0.68
    ſelf
    -0.67
     ddelweddau
    -0.63
    himself
    -0.61
    ſelves
    -0.59
     herself
    -0.58
     ―――――
    -0.56
     Shakspeare
    -0.56
    POSITIVE LOGITS
     they
    1.61
     we
    1.59
     it
    1.50
     there
    1.40
     you
    1.17
     he
    1.12
     this
    0.97
     I
    0.94
     the
    0.94
     these
    0.89
    Act Density 0.478%

    No Known Activations