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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positions or locations within a sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time or transitions within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.74
     namely
    -0.73
     listened
    -0.71
     msec
    -0.70
    note
    -0.70
     reprinted
    -0.67
    soever
    -0.67
     accompanied
    -0.67
     accordingly
    -0.66
    among
    -0.66
    POSITIVE LOGITS
     end
    1.08
     goal
    1.04
     conclusion
    1.00
     horizon
    0.97
     extremes
    0.96
     completion
    0.95
     goals
    0.93
     heights
    0.93
     forefront
    0.91
     endpoint
    0.89
    Act Density 0.193%

    No Known Activations