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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and academic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weirdly
    -0.60
     commonest
    -0.58
    NameInMap
    -0.57
     cosas
    -0.50
    endphp
    -0.50
    そういう
    -0.50
    ....)
    -0.49
     biß
    -0.48
     ...)
    -0.47
     thing
    -0.47
    POSITIVE LOGITS
    optionalTypeArgs
    0.55
     lecz
    0.55
     attire
    0.51
    犹如
    0.50
    casted
    0.49
    исленность
    0.49
     endast
    0.48
     transfieras
    0.47
    Jîn
    0.46
    SharedCtor
    0.46
    Act Density 3.100%

    No Known Activations