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

    Neuronpedia

    INDEX
    Explanations

    references to records and record-keeping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funny
    -0.46
     crazy
    -0.44
     coger
    -0.39
     Chou
    -0.38
     "
    -0.37
     Japanese
    -0.37
     Vogt
    -0.36
    masının
    -0.36
     French
    -0.35
     wollen
    -0.35
    POSITIVE LOGITS
     records
    1.24
     record
    1.20
     Record
    1.16
     Records
    1.11
     RECORD
    1.07
    record
    1.05
     RECORDS
    1.05
    Record
    0.99
    records
    0.96
    Records
    0.93
    Act Density 0.024%

    No Known Activations