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

    Neuronpedia

    INDEX
    Explanations

    references to time and duration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recently
    -0.43
     recent
    -0.39
    recent
    -0.36
     earlier
    -0.31
     currently
    -0.30
     Recently
    -0.28
    Recently
    -0.27
    currently
    -0.27
     presently
    -0.26
     lately
    -0.26
    POSITIVE LOGITS
     altern
    0.25
    avaÅŁ
    0.20
     whenever
    0.20
     gradually
    0.19
     alternating
    0.19
    kept
    0.18
     alternate
    0.18
     slowly
    0.18
     Altern
    0.17
     kept
    0.17
    Act Density 0.224%

    No Known Activations