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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media sharing or online interaction

    oai_token-act-pair · gpt-3.5-turbo

    commands related to user interactions, such as clicking to open or share content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.83
    cffff
    -0.79
    anship
    -0.75
    ntil
    -0.75
    ModLoader
    -0.72
    ©¶æ
    -0.71
    Whoever
    -0.70
     helicop
    -0.70
    ccording
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    POSITIVE LOGITS
     link
    0.81
     picture
    0.81
     source
    0.80
     gallery
    0.78
     citation
    0.73
     spoiler
    0.73
     miss
    0.72
     article
    0.72
     annotation
    0.72
     archived
    0.71
    Act Density 0.095%

    No Known Activations