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

    Neuronpedia

    INDEX
    Explanations

    contrasts or disagreements in beliefs or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.17
     heightFor
    -0.15
    idon
    -0.15
    ERM
    -0.15
    gos
    -0.14
    endir
    -0.14
    ÄĽst
    -0.14
    ãĤ«ãĥ¼
    -0.14
    gne
    -0.14
    ood
    -0.13
    POSITIVE LOGITS
    utor
    0.16
    lemen
    0.15
     Inspiration
    0.15
     Cave
    0.15
     Miguel
    0.14
    asaki
    0.13
    олом
    0.13
     Cannon
    0.13
     Mits
    0.13
     output
    0.13
    Act Density 0.410%

    No Known Activations