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

    Neuronpedia

    INDEX
    Explanations

    instructions or details regarding organizational policies or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Simms
    -0.65
    ing
    -0.63
    ledge
    -0.61
     cabo
    -0.60
     ban
    -0.60
     pant
    -0.59
     Vanden
    -0.59
     Kron
    -0.58
    oux
    -0.58
    aré
    -0.57
    POSITIVE LOGITS
     }}$}
    1.55
    }))
    1.46
    })$}
    1.40
    __':
    1.38
    </h2>
    1.32
    )}
    1.30
    .)}
    1.28
    )$}
    1.26
    </h4>
    1.25
    }]
    1.24
    Act Density 0.021%

    No Known Activations