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

    Neuronpedia

    INDEX
    Explanations

    terms related to investigative reporting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investigative journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -1.03
    creen
    -0.88
    jri
    -0.88
    unin
    -0.86
    ogun
    -0.83
    olen
    -0.81
    hops
    -0.79
    generic
    -0.78
    ivari
    -0.77
    aus
    -0.74
    POSITIVE LOGITS
     Investigative
    1.03
     investigative
    0.98
     journalism
    0.93
     investigations
    0.93
     Investigations
    0.88
     investigation
    0.88
     probing
    0.87
     journalist
    0.85
     Investigation
    0.82
     reporting
    0.82
    Act Density 0.029%

    No Known Activations