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

    Neuronpedia

    INDEX
    Explanations

    references to the release of reports or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lette
    -0.15
    Ñĩай
    -0.15
    VELO
    -0.15
    ickers
    -0.14
     xOffset
    -0.14
    RAFT
    -0.14
    ride
    -0.13
    affles
    -0.13
    æĹıèĩªæ²»
    -0.13
    ieder
    -0.13
    POSITIVE LOGITS
    myp
    0.15
     tut
    0.15
    ONTAL
    0.15
     clearance
    0.15
    utar
    0.15
    eselect
    0.14
    utes
    0.14
     Clearance
    0.14
    iously
    0.14
     domic
    0.14
    Act Density 0.052%

    No Known Activations