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

    Neuronpedia

    INDEX
    Explanations

    words indicating a sense of the current timeframe or context

    oai_token-act-pair · gpt-3.5-turbo

    the word "Now" indicating immediacy or current relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zag
    -0.72
     Airl
    -0.72
     [|
    -0.68
    acci
    -0.63
    vez
    -0.62
    ked
    -0.61
    tro
    -0.60
     Masquerade
    -0.60
    sac
    -0.58
    EVA
    -0.58
    POSITIVE LOGITS
    adays
    1.89
    here
    1.21
    heres
    0.88
    nir
    0.83
    ledge
    0.80
     Playing
    0.76
    herer
    0.73
    terday
    0.69
    olate
    0.67
     defunct
    0.66
    Act Density 0.044%

    No Known Activations