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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disagreement or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unt
    -0.15
    ãĥ©ãĤ¤ãĥĪ
    -0.15
    ãĤ¯ãĥĪ
    -0.14
    dept
    -0.14
     either
    -0.14
    ãĤ¯ãĤ·ãĥ§ãĥ³
    -0.14
    Ä«
    -0.13
    inst
    -0.13
    tron
    -0.13
    ult
    -0.13
    POSITIVE LOGITS
    heimer
    0.20
    OLON
    0.17
    olon
    0.17
    inati
    0.15
    ãĥ³ãĤ¬
    0.14
    fault
    0.14
    htar
    0.14
     CONTRIBUTORS
    0.14
    HEMA
    0.14
    sst
    0.13
    Act Density 0.061%

    No Known Activations