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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cancel" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.18
    ewise
    -0.17
     up
    -0.16
     a
    -0.16
     g
    -0.15
     pur
    -0.15
     rust
    -0.15
    Gatt
    -0.15
    WO
    -0.15
    sert
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĤ¯
    0.17
    oplay
    0.16
    HEME
    0.16
    æ²ĸ
    0.15
    agi
    0.15
     anytime
    0.15
    uve
    0.15
    Porno
    0.15
    Ế
    0.14
    OrFail
    0.14
    Act Density 0.001%

    No Known Activations