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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that are not standard letters or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .twitch
    -0.16
    (mc
    -0.15
     Vladim
    -0.15
    бÑĥдÑĮ
    -0.15
    IRR
    -0.15
     Fahr
    -0.14
     Qui
    -0.14
    lfw
    -0.14
     Cyr
    -0.14
    @Id
    -0.14
    POSITIVE LOGITS
     Scott
    0.20
     Green
    0.19
     Thomas
    0.18
     Blog
    0.18
     Carter
    0.17
     King
    0.17
     White
    0.17
     Nelson
    0.17
     Young
    0.17
     Ryan
    0.17
    Act Density 0.005%

    No Known Activations