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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that precede a specific symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.80
     lodging
    -0.66
     Libyan
    -0.64
     scatter
    -0.62
     Droid
    -0.62
     retreat
    -0.62
    ozy
    -0.62
     Sapphire
    -0.61
     RAD
    -0.61
     scattering
    -0.61
    POSITIVE LOGITS
    £
    1.09
    ¹
    1.06
    Ĵ
    0.99
    ı
    0.97
    º
    0.97
    ¡
    0.96
    ¸
    0.94
    Į
    0.94
    ¬
    0.94
    Ĭ
    0.93
    Act Density 0.343%

    No Known Activations