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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to the current document or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loose
    -0.16
    rels
    -0.15
    borough
    -0.14
     finish
    -0.14
    erus
    -0.14
    ̣
    -0.14
    _PERSON
    -0.13
    zman
    -0.13
     Lod
    -0.13
     æĿ¾
    -0.13
    POSITIVE LOGITS
     Angiospermae
    0.15
    iams
    0.14
    ezier
    0.14
    ãģĭãĤĬ
    0.13
    ailles
    0.13
    lernen
    0.13
    ANGLES
    0.13
    oldt
    0.13
    ppo
    0.13
    LETTE
    0.13
    Act Density 0.057%

    No Known Activations