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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sumpay
    -0.69
    +:+
    -0.63
     Signalez
    -0.59
    AddTagHelper
    -0.58
    әрмәләр
    -0.58
    MessageTagHelper
    -0.57
     gyhoeddwyd
    -0.56
    majánló
    -0.56
     通販
    -0.55
     мәкал
    -0.55
    POSITIVE LOGITS
     Yuan
    0.39
     Governor
    0.34
     Tu
    0.30
    GLint
    0.29
     Ambassador
    0.29
     run
    0.29
     President
    0.29
    WaitGroup
    0.28
    Mockito
    0.28
    FilterChain
    0.28
    Act Density 0.497%

    No Known Activations