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

    Neuronpedia

    INDEX
    Explanations

    references to significant factors or components in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dare
    -0.16
    uries
    -0.16
    ihan
    -0.16
    are
    -0.16
    ãģ¾ãģ¾
    -0.15
    addock
    -0.15
    igung
    -0.15
    uteur
    -0.15
    ESIS
    -0.15
    alle
    -0.14
    POSITIVE LOGITS
     reasons
    0.18
     things
    0.16
     else
    0.15
    reason
    0.15
    avel
    0.15
    lech
    0.15
    iales
    0.14
     î¡
    0.14
    things
    0.14
    esch
    0.14
    Act Density 0.012%

    No Known Activations