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

    Neuronpedia

    INDEX
    Explanations

    references to specific terminology or keywords related to fields and areas of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.11
     Cæsar
    -1.10
     Monfieur
    -1.04
     themſelves
    -1.04
     himſelf
    -1.03
     Majefty
    -1.02
     poffible
    -1.01
     pleaſure
    -0.94
     decorativas
    -0.93
     reaſon
    -0.93
    POSITIVE LOGITS
     Fields
    1.75
     fields
    1.69
     Field
    1.60
     field
    1.60
     getField
    1.57
     FIELD
    1.54
    fields
    1.51
    Fields
    1.50
     FIELDS
    1.44
    Field
    1.42
    Act Density 0.092%

    No Known Activations