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

    Neuronpedia

    INDEX
    Explanations

    questions about events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    questions related to introductions and how individuals came to be involved with specific topics or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reminders
    -0.69
    arer
    -0.64
     consolation
    -0.62
    arers
    -0.57
    illation
    -0.57
    ħĭ
    -0.57
    eware
    -0.57
     anytime
    -0.56
     caveats
    -0.56
     nightly
    -0.55
    POSITIVE LOGITS
     inception
    0.79
     genesis
    0.79
     originate
    0.75
     conception
    0.68
    Interested
    0.68
    aneous
    0.68
    !/
    0.67
    starter
    0.67
    Created
    0.66
     chose
    0.66
    Act Density 0.255%

    No Known Activations