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

    Neuronpedia

    INDEX
    Explanations

    references to pens or pen-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.87
     nahilalakip
    -0.81
    batore
    -0.80
     useStyles
    -0.73
    🤣🤣
    -0.72
     Shand
    -0.71
    dsm
    -0.70
     propOrder
    -0.70
    IDATE
    -0.70
    
    -0.70
    POSITIVE LOGITS
     pen
    1.61
    pen
    1.55
    Pen
    1.55
     Pen
    1.52
     Pens
    1.52
     PEN
    1.52
     pens
    1.49
    Pens
    1.45
     PENS
    1.36
    PEN
    1.33
    Act Density 0.213%

    No Known Activations