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

    Neuronpedia

    INDEX
    Explanations

    references to items, their conditions, and the process of repairing or replacing them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufe
    -0.15
    æİĴ
    -0.14
     Debt
    -0.14
    ovich
    -0.14
    .dismiss
    -0.13
    utex
    -0.13
     debt
    -0.13
    ÐIJÑĢÑħÑĸв
    -0.13
    .skin
    -0.13
     dolor
    -0.13
    POSITIVE LOGITS
     damaged
    0.39
    dam
    0.31
     broken
    0.29
     Dam
    0.27
     damage
    0.27
    Dam
    0.26
     badly
    0.26
     damages
    0.25
     missing
    0.25
     worn
    0.25
    Act Density 0.206%

    No Known Activations