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

    Neuronpedia

    INDEX
    Explanations

    the word "interesting" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    شرين
    -0.63
     ajutor
    -0.61
     tervez
    -0.61
     készült
    -0.60
     picioare
    -0.59
     kunjung
    -0.59
     secours
    -0.58
    ztály
    -0.55
    a
    -0.55
     segera
    -0.54
    POSITIVE LOGITS
    interesting
    1.38
     interesting
    1.26
    Interesting
    1.21
     Interesting
    1.12
     fascinating
    1.12
     curious
    1.02
     intriguing
    0.97
     intéressant
    0.96
     intéressante
    0.95
     curio
    0.94
    Act Density 0.101%

    No Known Activations