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

    Neuronpedia

    INDEX
    Explanations

    references to language learning platforms and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .sam
    -0.20
    owell
    -0.16
    oller
    -0.16
    acas
    -0.14
     SAM
    -0.14
    oles
    -0.14
    icha
    -0.14
     OPC
    -0.14
    builtin
    -0.14
    agas
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.14
     Sno
    0.14
    -Cs
    0.14
    alist
    0.14
    ysize
    0.14
     removeAll
    0.14
     졸
    0.14
    loo
    0.13
     trot
    0.13
    .gg
    0.13
    Act Density 0.011%

    No Known Activations