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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the introduction or discussion of comparisons and important points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amar
    -0.15
     pride
    -0.15
    omi
    -0.14
    å½¢
    -0.14
     Charm
    -0.13
    dig
    -0.13
    iy
    -0.13
     gro
    -0.13
     Pat
    -0.13
    eties
    -0.13
    POSITIVE LOGITS
    afil
    0.17
    θο
    0.16
    cpy
    0.15
    erdem
    0.15
    íĨłíĨł
    0.14
    nonnull
    0.14
    iedy
    0.14
    .newBuilder
    0.14
    chner
    0.14
    .Xaml
    0.14
    Act Density 0.040%

    No Known Activations