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

    Neuronpedia

    INDEX
    Explanations

    sentences or statements ending with a comma and a non-zero activation value word

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imagination
    -0.81
     puff
    -0.79
     stump
    -0.78
     idea
    -0.74
     likeness
    -0.72
     resemblance
    -0.71
     floppy
    -0.69
    è¦ļéĨĴ
    -0.69
     shape
    -0.67
    izen
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.16
    said
    0.98
    tra
    0.92
    ¯
    0.91
    âĢł
    0.85
    #$
    0.85
    mr
    0.81
    Pg
    0.81
    east
    0.81
    ttp
    0.81
    Act Density 0.206%

    No Known Activations