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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "news" and related terms indicating news contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erval
    -0.16
    Unchecked
    -0.15
    Ñıн
    -0.14
    andle
    -0.14
    pressions
    -0.14
    ald
    -0.14
    endas
    -0.14
    ibri
    -0.13
    enge
    -0.13
    ç´
    -0.13
    POSITIVE LOGITS
    ysa
    0.14
    511
    0.14
     Tam
    0.14
    ROOM
    0.14
    669
    0.14
    cpt
    0.14
     Tes
    0.13
    Tes
    0.13
    ynet
    0.13
    cus
    0.13
    Act Density 0.074%

    No Known Activations