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

    Neuronpedia

    INDEX
    Explanations

    terms related to journalism, including job titles and actions related to news reporting

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments or criticisms related to individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.90
    ylon
    -0.70
     Burr
    -0.68
     Cotton
    -0.65
     Bullets
    -0.64
     Downs
    -0.64
     Cros
    -0.64
     Dial
    -0.64
     Indigo
    -0.63
     Blu
    -0.63
    POSITIVE LOGITS
    friendly
    1.13
    controlled
    1.09
    turned
    1.08
    sized
    1.07
    based
    1.07
    centric
    1.05
    dominated
    1.03
    style
    1.02
    driven
    1.02
    loving
    1.01
    Act Density 0.151%

    No Known Activations