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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to implementation and targeted actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieg
    -0.17
     FX
    -0.16
    VOKE
    -0.15
     B
    -0.15
    avy
    -0.14
     Inf
    -0.14
    oblin
    -0.14
     Purs
    -0.14
    ablo
    -0.13
    INA
    -0.13
    POSITIVE LOGITS
     Aspect
    0.17
    iren
    0.16
     memorial
    0.15
    celik
    0.15
    .cy
    0.14
     Basin
    0.14
    ارش
    0.14
    zap
    0.14
    887
    0.14
    Aspect
    0.14
    Act Density 0.004%

    No Known Activations