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

    Neuronpedia

    INDEX
    Explanations

    organizations or agencies involved in research and estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amage
    -0.16
    ikat
    -0.16
    849
    -0.15
    volt
    -0.15
     onBind
    -0.14
    istrovstvÃŃ
    -0.14
    .responses
    -0.13
    IID
    -0.13
    веÑī
    -0.13
    -inv
    -0.13
    POSITIVE LOGITS
     projects
    0.27
     report
    0.27
     released
    0.25
     reported
    0.23
     peg
    0.23
     release
    0.22
     class
    0.22
     recently
    0.22
     releasing
    0.22
     calculates
    0.21
    Act Density 0.092%

    No Known Activations