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

    Neuronpedia

    INDEX
    Explanations

    questions and interrogative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seldom
    -0.15
     rarely
    -0.15
    íĮ
    -0.14
     often
    -0.14
     लà¤Ĺत
    -0.13
     nowhere
    -0.13
    dbl
    -0.13
    ovice
    -0.13
    기ëıĦ
    -0.13
     uno
    -0.12
    POSITIVE LOGITS
     happened
    0.25
     planet
    0.24
     possessed
    0.23
     else
    0.22
     kind
    0.21
     nationality
    0.21
     century
    0.21
     direction
    0.20
     color
    0.20
     continent
    0.19
    Act Density 0.116%

    No Known Activations