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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate perception or observation, particularly in relation to feelings or appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shed
    -0.15
    /trunk
    -0.14
     Coin
    -0.14
    pper
    -0.14
    eon
    -0.13
    ifu
    -0.13
    PILE
    -0.13
     воÑĤ
    -0.13
    ustral
    -0.13
    ago
    -0.13
    POSITIVE LOGITS
     from
    0.26
    from
    0.21
     từ
    0.20
     dari
    0.20
     ä»İ
    0.19
    à¸Īาà¸ģ
    0.19
     by
    0.19
    	from
    0.19
    ä»İ
    0.19
     från
    0.19
    Act Density 0.082%

    No Known Activations