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

    Neuronpedia

    INDEX
    Explanations

    expressions of fascination or interest in various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issauga
    -0.67
    ztály
    -0.64
     czu
    -0.63
    édie
    -0.59
     tervez
    -0.57
    μαστε
    -0.55
     bertujuan
    -0.55
    formis
    -0.55
     gyakor
    -0.54
     vectorielle
    -0.52
    POSITIVE LOGITS
     interesting
    1.50
    interesting
    1.48
     Interesting
    1.35
    Interesting
    1.34
     intriguing
    1.27
     fascinating
    1.23
     interesante
    1.19
     interessante
    1.16
     intéressante
    1.16
     interessant
    1.12
    Act Density 0.202%

    No Known Activations