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

    Neuronpedia

    INDEX
    Explanations

    specific symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     winds
    -0.66
     juggling
    -0.66
    iage
    -0.61
     mushroom
    -0.61
    ioxide
    -0.60
     garden
    -0.59
     fly
    -0.57
     cleaner
    -0.56
    rent
    -0.56
     runaway
    -0.55
    POSITIVE LOGITS
     âĢ
    3.86
    âĢ
    2.41
    âĢł
    1.57
     **
    1.34
     âĶ
    1.33
     â
    1.24
    âģ
    1.24
     ðŁij
    1.21
     âĩ
    1.19
     ¶
    1.18
    Act Density 0.264%

    No Known Activations