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

    Neuronpedia

    INDEX
    Explanations

    phrases related to current events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.78
    phies
    -0.78
    cot
    -0.74
    alty
    -0.73
    pose
    -0.73
    rete
    -0.72
    issue
    -0.71
     Parables
    -0.71
    oug
    -0.71
    ocl
    -0.71
    POSITIVE LOGITS
    uate
    0.94
     unfolding
    0.75
     unfold
    0.74
    uated
    0.73
     everywhere
    0.73
    uates
    0.73
     Archdemon
    0.72
     around
    0.69
    uating
    0.68
     havoc
    0.68
    Act Density 0.032%

    No Known Activations