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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases and their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.76
     demikian
    -0.64
    archiviato
    -0.60
     quite
    -0.60
     justement
    -0.58
     minOccurs
    -0.55
     незавершена
    -0.55
     olyan
    -0.55
     however
    -0.54
     certainly
    -0.54
    POSITIVE LOGITS
     betweenstory
    0.80
    ...:
    0.74
     ?:
    0.70
    !:
    0.70
     Lordships
    0.67
    .../
    0.65
     ويكيميديا
    0.65
    horesis
    0.64
     따
    0.62
    :✨
    0.61
    Act Density 0.901%

    No Known Activations