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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or occurrences happening in a particular round or stage of a process

    oai_token-act-pair · gpt-3.5-turbo

    references to rounds of discussions or negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.71
    itud
    -0.70
    ilk
    -0.69
     summed
    -0.69
    ose
    -0.69
    sense
    -0.68
    rider
    -0.67
    ername
    -0.66
    esse
    -0.66
    ghan
    -0.65
    POSITIVE LOGITS
     applause
    1.18
     negotiations
    1.02
     hostilities
    1.01
     layoffs
    0.98
     engagements
    0.91
     deployments
    0.89
     hearings
    0.86
     trials
    0.85
     festivities
    0.85
     tests
    0.84
    Act Density 0.077%

    No Known Activations