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

    Neuronpedia

    INDEX
    Explanations

    information related to investigations and reports

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations and reports related to news or data disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preferably
    -0.71
    itely
    -0.70
    must
    -0.70
     depends
    -0.70
    ":"/
    -0.69
    =-=-=-=-=-=-=-=-
    -0.66
     SHALL
    -0.64
     suffice
    -0.62
    please
    -0.60
     TBA
    -0.60
    POSITIVE LOGITS
     indicating
    1.10
     suggesting
    1.09
     showing
    1.02
     revealing
    0.99
     alleging
    0.97
     accusing
    0.97
     highlighting
    0.96
     earlier
    0.96
     wherein
    0.95
     announcing
    0.95
    Act Density 0.430%

    No Known Activations