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

    Neuronpedia

    INDEX
    Explanations

    instances of brackets or special punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vais
    -0.17
    inki
    -0.16
     Tomorrow
    -0.15
    ailability
    -0.15
    NV
    -0.15
     fork
    -0.14
     Mare
    -0.14
     tomorrow
    -0.14
    uste
    -0.14
     Bair
    -0.14
    POSITIVE LOGITS
     Sokol
    0.19
    exact
    0.15
    izers
    0.14
    968
    0.14
    foods
    0.14
     {{↵
    0.14
    è¼
    0.14
    497
    0.14
    853
    0.13
    .uni
    0.13
    Act Density 0.028%

    No Known Activations