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

    Neuronpedia

    INDEX
    Explanations

    references to 'the latter' in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.16
     nie
    -0.15
    rade
    -0.15
    ģ
    -0.14
    stad
    -0.14
     packed
    -0.13
    alo
    -0.13
    orman
    -0.13
     Northern
    -0.13
     Halk
    -0.13
    POSITIVE LOGITS
    vero
    0.15
    ifle
    0.15
    rema
    0.15
    ANNEL
    0.14
    orch
    0.14
    /vnd
    0.14
    ech
    0.14
     éĤ
    0.14
    iot
    0.14
    reffen
    0.14
    Act Density 0.005%

    No Known Activations