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

    Neuronpedia

    INDEX
    Explanations

    the names of specific news outlets and journalists

    oai_token-act-pair · gpt-3.5-turbo

    prominent media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.85
    chwitz
    -0.68
    aturday
    -0.68
    ailability
    -0.67
    comfort
    -0.65
     âĵĺ
    -0.65
    rontal
    -0.65
    posure
    -0.64
    istries
    -0.63
    auri
    -0.63
    POSITIVE LOGITS
     progresses
    1.12
     unfolds
    0.99
     grows
    0.93
     expands
    0.83
     evolves
    0.83
     begins
    0.80
     prepares
    0.78
     progressed
    0.77
     unfolded
    0.77
     continues
    0.77
    Act Density 0.275%

    No Known Activations