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

    Neuronpedia

    INDEX
    Explanations

    terms related to media and press interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مواليد
    -0.51
    engr
    -0.49
    Liefs
    -0.48
    ochond
    -0.46
    ([]
    -0.46
     McRae
    -0.45
    tableFuture
    -0.45
     poème
    -0.44
    oucí
    -0.44
    imiz
    -0.44
    POSITIVE LOGITS
     journalists
    1.15
     reporters
    1.10
     Journalists
    1.03
     journalism
    1.02
     journalistic
    1.01
     journalist
    1.01
     publicity
    1.00
     Reporters
    0.95
     newspapers
    0.95
     news
    0.94
    Act Density 0.347%

    No Known Activations