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

    Neuronpedia

    INDEX
    Explanations

    various forms and usages of the word "ink."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gings
    -0.18
     Beled
    -0.17
    zia
    -0.17
    esty
    -0.16
    zar
    -0.16
    LOCKS
    -0.15
     tumble
    -0.15
    ipmap
    -0.14
    otte
    -0.14
    ndef
    -0.14
    POSITIVE LOGITS
    ed
    0.21
    horn
    0.21
    ling
    0.18
    holes
    0.18
    hole
    0.17
    ler
    0.17
    ognito
    0.17
    -tank
    0.17
     Tank
    0.16
    elman
    0.16
    Act Density 0.015%

    No Known Activations