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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives indicating popularity or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itler
    -0.19
    iated
    -0.16
    trys
    -0.16
    strup
    -0.16
    ãģĵãģĿ
    -0.16
     more
    -0.15
    .less
    -0.14
    irtual
    -0.14
    å¾Ī
    -0.14
    isan
    -0.14
    POSITIVE LOGITS
    -talk
    0.21
    afa
    0.19
     talked
    0.18
    -request
    0.18
     likely
    0.17
     important
    0.16
     recent
    0.16
    aghan
    0.16
    -complete
    0.16
     complete
    0.16
    Act Density 0.058%

    No Known Activations