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

    Neuronpedia

    INDEX
    Explanations

    terms related to the writing and editing process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tub
    -0.17
    inated
    -0.16
    babel
    -0.15
    HWND
    -0.14
    rade
    -0.14
    kus
    -0.14
    ople
    -0.14
    etim
    -0.14
    lasses
    -0.13
    chein
    -0.13
    POSITIVE LOGITS
     rough
    0.18
     Later
    0.16
    -transitional
    0.16
     Rough
    0.16
     early
    0.15
     bul
    0.15
    çiler
    0.15
    early
    0.15
     lorem
    0.15
     dummy
    0.14
    Act Density 0.019%

    No Known Activations