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

    Neuronpedia

    INDEX
    Explanations

    mentions of expenses related to specific items or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to decorative plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.78
    £ı
    -0.77
    NetMessage
    -0.77
    ¥µ
    -0.74
     Harmony
    -0.70
     pac
    -0.70
     proverb
    -0.66
     antioxid
    -0.66
     Juda
    -0.66
     laure
    -0.66
    POSITIVE LOGITS
     LGBTQ
    0.68
    clusive
    0.67
    anke
    0.65
    lees
    0.65
    herent
    0.65
    ulty
    0.65
    rator
    0.64
    ###
    0.64
     entirety
    0.63
    kell
    0.63
    Act Density 0.000%

    No Known Activations