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

    Neuronpedia

    INDEX
    Explanations

    terms related to announcements, news, and information dissemination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to news and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.77
    riages
    -0.74
    awatts
    -0.71
    ernels
    -0.70
    nings
    -0.68
    Americans
    -0.68
    waves
    -0.67
    chens
    -0.67
     dads
    -0.65
    rices
    -0.65
    POSITIVE LOGITS
     standpoint
    0.94
     agent
    0.88
     advisory
    0.85
     counselor
    0.82
     regime
    0.80
    icer
    0.80
     program
    0.79
     outlet
    0.79
     bubble
    0.78
     department
    0.78
    Act Density 0.472%

    No Known Activations