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

    Neuronpedia

    INDEX
    Explanations

    expressions of criticism and criticism-related vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ги
    -0.16
    enha
    -0.16
    ki
    -0.15
    allet
    -0.15
     identity
    -0.14
    絡
    -0.14
    cki
    -0.14
    czy
    -0.14
     bore
    -0.14
     Madness
    -0.14
    POSITIVE LOGITS
    acos
    0.17
    oise
    0.16
    IPA
    0.16
    acas
    0.15
    bersome
    0.14
    asting
    0.14
    ingly
    0.14
     hur
    0.14
     ADVISED
    0.13
     Samar
    0.13
    Act Density 0.063%

    No Known Activations