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

    Neuronpedia

    INDEX
    Explanations

    phrases that express contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç³»
    -0.15
    aben
    -0.14
    ahoo
    -0.14
    оло
    -0.14
     cov
    -0.14
    (er
    -0.13
    ovu
    -0.13
     spring
    -0.13
    rames
    -0.13
    uctor
    -0.13
    POSITIVE LOGITS
    adil
    0.19
    arro
    0.16
    dG
    0.16
    avel
    0.15
     REFERENCES
    0.14
    cano
    0.14
     Leadership
    0.14
    EMA
    0.14
    Americ
    0.14
    èm
    0.13
    Act Density 0.043%

    No Known Activations