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

    Neuronpedia

    INDEX
    Explanations

    references or prompts to engage with the comments section of an online platform

    oai_token-act-pair · gpt-3.5-turbo

    references to user comments and engagement prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISM
    -0.88
    relative
    -0.81
    agall
    -0.73
     Relative
    -0.69
    Ct
    -0.67
    cci
    -0.66
     Illegal
    -0.65
    NetMessage
    -0.64
    isen
    -0.64
    Definition
    -0.64
    POSITIVE LOGITS
     comments
    0.80
     section
    0.77
     below
    0.76
    pring
    0.75
     Gle
    0.69
     sections
    0.69
    below
    0.69
     favourites
    0.67
    antha
    0.66
     box
    0.66
    Act Density 0.057%

    No Known Activations