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

    Neuronpedia

    INDEX
    Explanations

    recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "recently" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.78
    eers
    -0.71
    sure
    -0.67
    eer
    -0.62
     strictly
    -0.62
    emen
    -0.61
     simulac
    -0.61
     Likely
    -0.61
    uming
    -0.60
    amination
    -0.59
    POSITIVE LOGITS
     resur
    0.85
     unearthed
    0.85
     updated
    0.83
     renovated
    0.82
     undergone
    0.79
     concluded
    0.78
     declass
    0.78
     published
    0.77
     announced
    0.77
     reopened
    0.77
    Act Density 0.052%

    No Known Activations