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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific person or place, likely related to the name "Cho"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cho" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doors
    -0.88
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    dash
    -0.67
    Definition
    -0.66
    RANT
    -0.65
    FORMATION
    -0.63
    Reloaded
    -0.63
    night
    -0.63
    vae
    -0.62
    working
    -0.62
    POSITIVE LOGITS
    ices
    1.04
    oser
    1.02
    osing
    0.99
    oldown
    0.96
    pper
    0.95
    iral
    0.90
     Cho
    0.88
    iced
    0.88
    icer
    0.86
    pped
    0.85
    Act Density 0.008%

    No Known Activations