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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future plans or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upert
    -0.20
    upp
    -0.18
    avra
    -0.16
    anooga
    -0.15
    lesia
    -0.14
    Æ°ng
    -0.14
    enÄĽ
    -0.14
    æĨ¶
    -0.14
    ushima
    -0.13
    upro
    -0.13
    POSITIVE LOGITS
     to
    0.24
     ahead
    0.23
     toward
    0.23
     set
    0.21
     towards
    0.21
     beyond
    0.20
     Ahead
    0.20
     likely
    0.19
     east
    0.18
     optim
    0.18
    Act Density 0.038%

    No Known Activations