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

    Neuronpedia

    INDEX
    Explanations

    references to intellectual property or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bleach
    -0.80
     RL
    -0.68
    OWS
    -0.67
    OSS
    -0.67
     Passing
    -0.67
     RELE
    -0.67
    ¡
    -0.67
    OW
    -0.65
     319
    -0.65
     Bearing
    -0.64
    POSITIVE LOGITS
    m
    1.10
    mill
    0.99
    mo
    0.99
    mic
    0.97
    mad
    0.96
    mob
    0.94
    mom
    0.94
    mort
    0.94
    mot
    0.93
    mia
    0.91
    Act Density 0.226%

    No Known Activations