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

    Neuronpedia

    INDEX
    Explanations

    words that end with specific suffixes or are in gerund forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.28
     raiſ
    -1.26
     Eſ
    -1.16
     Jefus
    -1.14
     iſt
    -1.12
     myſelf
    -1.11
     ſche
    -1.07
     deſt
    -1.06
     anſ
    -1.05
     Conſ
    -1.04
    POSITIVE LOGITS
    
    0.84
     createState
    0.64
    )]=
    0.58
     
    0.56
    OGND
    0.53
    uinal
    0.53
     StatelessWidget
    0.53
    帖最后由
    0.52
     Dud
    0.52
    JspWriter
    0.52
    Act Density 0.200%

    No Known Activations