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

    Neuronpedia

    INDEX
    Explanations

    references or citations from academic or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.13
    VERTISEMENT
    -1.05
    leſs
    -1.03
    tagHelperRunner
    -0.99
    ſhip
    -0.99
     
    -0.97
    ENEFITS
    -0.95
    extAlignment
    -0.91
     ―――――
    -0.91
    eſt
    -0.90
    POSITIVE LOGITS
    .
    2.25
    。
    1.65
    ).
    1.60
    ].
    1.51
    ।
    1.47
    }$.
    1.46
    ().
    1.44
    ".
    1.39
    $.
    1.39
    }.
    1.36
    Act Density 3.332%

    No Known Activations