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

    Neuronpedia

    INDEX
    Explanations

    references to editing and alterations in historical or textual narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orea
    -0.16
    ldb
    -0.14
    æ¥ŃåĭĻ
    -0.14
     misuse
    -0.14
    podob
    -0.14
    ξι
    -0.14
    ÑģÑĤаÑĤи
    -0.14
    inkel
    -0.13
    atik
    -0.13
    undred
    -0.13
    POSITIVE LOGITS
     removed
    0.29
     removing
    0.25
     removal
    0.25
     remove
    0.24
     addition
    0.24
     Addition
    0.24
     removes
    0.23
     added
    0.23
     inserted
    0.22
    æ·»åĬł
    0.22
    Act Density 0.221%

    No Known Activations