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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kla
    -0.16
    uiten
    -0.16
    ìĸµ
    -0.15
    òng
    -0.15
     Bundy
    -0.14
     Farmer
    -0.14
     interpol
    -0.14
    ouis
    -0.14
    Ãłi
    -0.14
     Wellington
    -0.13
    POSITIVE LOGITS
     Neutral
    0.20
     Indoor
    0.17
     Marr
    0.17
     Lal
    0.17
    Neutral
    0.17
     Abb
    0.17
     Punch
    0.16
     Lid
    0.16
     Auburn
    0.16
     Roz
    0.15
    Act Density 0.042%

    No Known Activations