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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols that may indicate formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    desk
    -0.16
    752
    -0.16
     Immigration
    -0.15
    asp
    -0.15
    ÂŃs
    -0.15
    ÃĹ↵↵
    -0.15
    ilion
    -0.15
    ody
    -0.15
    742
    -0.14
    iesen
    -0.14
    POSITIVE LOGITS
    »
    0.33
    ¿
    0.32
    ¼
    0.28
    ¾
    0.26
    ½
    0.23
    ½Ķ
    0.21
     Bain
    0.18
    alom
    0.17
    Ê
    0.17
     mrb
    0.16
    Act Density 0.004%

    No Known Activations