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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions indicating a duration or delay

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate time-related expectations or delays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áµ
    -0.91
    Ë
    -0.80
    advertisement
    -0.78
    hid
    -0.78
    tw
    -0.76
    ãĤ©
    -0.75
    ¸
    -0.74
    ï
    -0.72
    cens
    -0.72
    kt
    -0.71
    POSITIVE LOGITS
     anyone
    1.05
     anybody
    0.93
     realization
    0.89
     anything
    0.88
     someone
    0.87
     we
    0.81
     conclusive
    0.81
     any
    0.78
     somebody
    0.78
     fully
    0.76
    Act Density 0.177%

    No Known Activations