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

    Neuronpedia

    INDEX
    Explanations

    references to the timing or urgency of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atin
    -0.75
    lua
    -0.71
    uay
    -0.65
     plurality
    -0.65
     comr
    -0.64
    utenberg
    -0.63
    ingen
    -0.62
    eq
    -0.60
    guyen
    -0.59
     Parables
    -0.58
    POSITIVE LOGITS
     thereafter
    0.90
    aneously
    0.80
    mint
    0.76
    iatus
    0.74
     arrives
    0.69
     regretted
    0.66
     horizon
    0.66
    .*
    0.65
     after
    0.61
    .
    0.61
    Act Density 0.036%

    No Known Activations