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

    Neuronpedia

    INDEX
    Explanations

    references to specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the urgency or whether a particular moment has arrived

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbai
    -0.78
    ammy
    -0.69
    ossier
    -0.65
    stic
    -0.64
    illac
    -0.64
    ppa
    -0.63
    acid
    -0.61
     Featured
    -0.61
    ffiti
    -0.61
     plagiar
    -0.61
    POSITIVE LOGITS
     ripe
    1.12
     ticking
    0.80
     wisely
    0.78
     elapsed
    0.78
     allotted
    0.77
     expired
    0.72
    200000
    0.72
    limits
    0.70
     expended
    0.68
     NOW
    0.67
    Act Density 0.099%

    No Known Activations