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

    Neuronpedia

    INDEX
    Explanations

    references to mainstream media and its influence on public discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¥
    -0.15
    eh
    -0.15
    ük
    -0.14
    -wow
    -0.14
     Pist
    -0.14
    ekten
    -0.13
    acho
    -0.13
    utzer
    -0.13
    long
    -0.13
    .Agent
    -0.13
    POSITIVE LOGITS
     outlets
    0.17
     outlet
    0.15
    /media
    0.14
    oka
    0.14
    uper
    0.14
    KeyValue
    0.14
    ofs
    0.14
    osit
    0.14
    iad
    0.14
    åªĴä½ĵ
    0.13
    Act Density 0.079%

    No Known Activations