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

    Neuronpedia

    INDEX
    Explanations

    words indicating a positive outcome or good fortune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģķãĤī
    -0.16
    borg
    -0.15
    ynamo
    -0.15
    adelphia
    -0.15
    ahan
    -0.15
    ãn
    -0.14
    ilet
    -0.14
    essional
    -0.14
    orks
    -0.14
    indsay
    -0.14
    POSITIVE LOGITS
    &action
    0.15
    (?
    0.14
    gate
    0.14
    è¿ĺæľī
    0.14
     Xm
    0.13
    ä¹Łæľī
    0.13
     Bott
    0.13
    shine
    0.13
    Latch
    0.13
    ModifiedDate
    0.13
    Act Density 0.038%

    No Known Activations