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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commentary or explanation

    oai_token-act-pair · gpt-3.5-turbo

    key ideas and important events related to political and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     torpedo
    -0.68
    kefeller
    -0.60
     pigeon
    -0.59
    owship
    -0.57
    wine
    -0.56
    grain
    -0.55
    destroy
    -0.55
    redit
    -0.54
     Rhodes
    -0.54
    uffed
    -0.53
    POSITIVE LOGITS
    âĢ
    1.86
     âĢ
    1.59
    ãĢ
    1.21
    *,
    1.06
    âĢł
    1.04
    âĶ
    1.02
    ï¸
    1.02
    âĻ
    1.01
    â
    1.01
     âĶ
    1.00
    Act Density 0.412%

    No Known Activations