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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly in structured contexts like data tables, references, or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.93
     ());
    -0.80
    HideFlags
    -0.80
    !")
    -0.80
    .")
    -0.77
    .)}
    -0.76
    awtextra
    -0.76
     "];
    -0.75
    .";
    -0.75
     ]
    -0.73
    POSITIVE LOGITS
    *
    1.78
    **
    1.49
    *,
    1.48
    *.
    1.40
     *
    1.37
    <sup>
    1.33
    *(
    1.31
    (*
    1.31
    .*
    1.28
    †
    1.26
    Act Density 1.150%

    No Known Activations