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

    Neuronpedia

    INDEX
    Explanations

    mentions of changes or modifications in legal or official documents

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "amend."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ§
    -0.81
    Fall
    -0.74
    gins
    -0.70
    fall
    -0.68
    metal
    -0.68
    á
    -0.68
    natureconservancy
    -0.67
    pled
    -0.67
    zees
    -0.66
    Ps
    -0.65
    POSITIVE LOGITS
    ments
    0.86
    xual
    0.81
    terday
    0.79
    ippi
    0.75
    ive
    0.73
     misunder
    0.71
    urous
    0.70
     clarify
    0.70
    ingly
    0.68
     defences
    0.68
    Act Density 0.023%

    No Known Activations