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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation marks and ellipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĦãģ¾ãģĻ
    -0.20
    rd
    -0.19
    -quarters
    -0.17
    ades
    -0.17
    çİĩ
    -0.16
    ington
    -0.16
    ning
    -0.16
    addtogroup
    -0.16
    oldem
    -0.16
    -ending
    -0.15
    POSITIVE LOGITS
    nd
    0.19
    ....↵↵
    0.18
    uai
    0.15
    /system
    0.15
    yal
    0.15
    -thirds
    0.15
    ãģĤãĤĬ
    0.15
    TRS
    0.15
    uality
    0.14
    cent
    0.14
    Act Density 0.054%

    No Known Activations