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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or companies

    oai_token-act-pair · gpt-3.5-turbo

    names of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tomorrow
    -0.93
     tonight
    -0.81
     resolves
    -0.78
     resumes
    -0.77
     proceeds
    -0.75
    morrow
    -0.70
     progresses
    -0.70
     rises
    -0.70
     responds
    -0.70
     Adds
    -0.68
    POSITIVE LOGITS
     famously
    1.00
     boasted
    0.96
     contemplated
    0.89
     oversaw
    0.87
     advocated
    0.86
     joked
    0.86
     faced
    0.85
     relied
    0.85
     lamented
    0.84
     experimented
    0.83
    Act Density 0.387%

    No Known Activations