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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
    帖最后由
    -0.57
    发表于
    -0.57
    grà
    -0.56
    }}</
    -0.55
    encodeWith
    -0.55
    RegressionTest
    -0.53
    ;#
    -0.52
    Demografia
    -0.51
    htë
    -0.50
    POSITIVE LOGITS
    TableHead
    0.63
     Suppl
    0.61
    SequentialGroup
    0.61
    
    0.57
    LookAnd
    0.56
    TagMode
    0.56
     autorytatywna
    0.54
    ArgsConstructor
    0.54
    contentLoaded
    0.53
     demurrer
    0.52
    Act Density 0.294%

    No Known Activations