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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ents
    -0.16
     mob
    -0.15
     Vor
    -0.15
    ãĥ¼ãĥª
    -0.14
    lotte
    -0.14
    ุà¸ģ
    -0.14
    zell
    -0.14
    stroy
    -0.14
    reatest
    -0.14
    ëĿ½
    -0.14
    POSITIVE LOGITS
     Randall
    0.19
     dark
    0.18
     SM
    0.17
     Dark
    0.17
     collider
    0.16
     MSS
    0.16
     scenarios
    0.16
    Dark
    0.16
     mrb
    0.16
    dark
    0.15
    Act Density 0.010%

    No Known Activations