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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to inequalities and equalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cauſe
    -0.66
     ſeveral
    -0.62
     preſent
    -0.62
     paſſ
    -0.61
     myſelf
    -0.61
     deſt
    -0.59
     beſ
    -0.59
     ſet
    -0.57
     tranſ
    -0.57
     purpoſe
    -0.57
    POSITIVE LOGITS
    >=</
    1.07
    }=
    1.07
    )}=
    1.03
    })=
    1.02
    }}=
    0.97
    )=
    0.94
    }=\
    0.93
     }}=
    0.89
    })=\
    0.89
    ))=
    0.87
    Act Density 0.632%

    No Known Activations