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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andaag
    -0.65
    LastModified
    -0.60
    RegressionTest
    -0.55
    <?
    -0.55
    IContainer
    -0.55
     RSSSF
    -0.55
    cipated
    -0.53
     Somit
    -0.53
     Fazit
    -0.52
     eſt
    -0.51
    POSITIVE LOGITS
     not
    0.77
     like
    0.77
    WriteBarrier
    0.75
     literally
    0.73
     maybe
    0.73
     both
    0.68
     a
    0.68
     the
    0.65
     نه
    0.63
     برانيه
    0.62
    Act Density 0.258%

    No Known Activations