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

    Neuronpedia

    INDEX
    Explanations

    numeric values or symbols associated with various measurements or parameters in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ={({
    -0.86
    hui
    -0.73
     ARA
    -0.72
    Raptor
    -0.70
    thora
    -0.70
    gogo
    -0.69
     trat
    -0.68
     Tato
    -0.68
    SENS
    -0.68
     ====
    -0.67
    POSITIVE LOGITS
    .^
    1.26
    )^
    1.26
    ]^
    1.23
    '^
    1.22
     ^
    1.20
    })^
    1.17
    }}^
    1.16
    ^^^
    1.16
    }^
    1.13
    :^
    1.08
    Act Density 0.445%

    No Known Activations