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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åıªæĺ¯
    -0.17
    are
    -0.16
    lez
    -0.16
    zan
    -0.16
    zelf
    -0.15
    onders
    -0.15
    antine
    -0.14
    Ñĸв
    -0.14
    iare
    -0.14
    ãĤĤãģªãģĦ
    -0.14
    POSITIVE LOGITS
    fans
    0.25
    Fans
    0.24
    íģ¼
    0.21
     rarely
    0.20
     partially
    0.20
     partly
    0.17
    yyyy
    0.17
    yyy
    0.17
     baÅŁÄ±na
    0.17
    ness
    0.17
    Act Density 0.085%

    No Known Activations