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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables related to statistical analysis and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }}_
    -0.81
    })^
    -0.75
    }}^
    -0.72
    )}_
    -0.70
    }/
    -0.69
    ))^
    -0.63
    }_
    -0.63
    }}.
    -0.62
    }^
    -0.61
    <eos>
    -0.61
    POSITIVE LOGITS
     enfans
    0.83
     Agamemnon
    0.76
     Cæsar
    0.76
     \
    0.76
     \&
    0.75
    konomi
    0.74
    $
    0.73
     polaire
    0.72
     avoit
    0.71
     Armenians
    0.68
    Act Density 1.202%

    No Known Activations