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

    Neuronpedia

    INDEX
    Explanations

    vertical lines and backslashes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSet
    -0.77
    TemporalType
    -0.74
     EFF
    -0.72
    ness
    -0.72
     gynhyrchwyd
    -0.72
    aktif
    -0.70
     Crook
    -0.70
    oredCriteria
    -0.70
     Schroeder
    -0.69
     trick
    -0.68
    POSITIVE LOGITS
     \\
    1.79
     \\\
    1.23
    \}\\
    1.22
    ?\\
    1.16
    </td>
    1.12
    ;\\
    1.09
    }}$\\
    1.07
    :\\
    1.05
    </tr>
    1.05
    ]\\
    1.05
    Act Density 0.021%

    No Known Activations