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

    Neuronpedia

    INDEX
    Explanations

    phrases related to journalism and investigative reporting

    oai_token-act-pair · gpt-3.5-turbo

    instances of sensationalized or biased reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -1.01
    psons
    -0.95
     sidx
    -0.82
    viks
    -0.82
    endants
    -0.81
    rils
    -0.80
    ptoms
    -0.78
    uders
    -0.78
     Defendants
    -0.76
    angered
    -0.73
    POSITIVE LOGITS
     journalism
    1.52
     economics
    1.36
     politics
    1.34
     diplomacy
    1.32
     filmmaking
    1.28
     lawy
    1.22
    manship
    1.21
     activism
    1.19
     medicine
    1.18
     warfare
    1.17
    Act Density 0.671%

    No Known Activations