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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relational or possessive references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĪãģĨãģª
    -0.19
    ãģĬ
    -0.19
    ä¸ĢåĪĩ
    -0.17
    大
    -0.16
    åŃIJä¾Ľ
    -0.16
    ä¸Ģ
    -0.16
     Äijây
    -0.15
    人æ°Ĺ
    -0.15
    orem
    -0.15
    fan
    -0.15
    POSITIVE LOGITS
     sorts
    0.38
    course
    0.32
     course
    0.27
    0.26
    vido
    0.25
    -course
    0.25
    ftime
    0.22
    /from
    0.21
    /by
    0.21
    lox
    0.20
    Act Density 1.823%

    No Known Activations