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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of 'less' or reduction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.15
    emoc
    -0.15
    .setView
    -0.15
    .microsoft
    -0.15
    tein
    -0.15
    uther
    -0.14
    olec
    -0.14
    oug
    -0.14
    ter
    -0.14
    astic
    -0.14
    POSITIVE LOGITS
    ening
    0.22
    eren
    0.17
    mate
    0.17
    ened
    0.16
    ere
    0.16
    any
    0.15
    azen
    0.14
    rita
    0.14
    ling
    0.14
     actively
    0.14
    Act Density 0.027%

    No Known Activations