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

    Neuronpedia

    INDEX
    Explanations

    nouns related to entities or subjects within various contexts

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

    preceding possessive "'s"

    np_acts-logits-general · gemini-2.0-flash

    subject nouns' qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -1.24
     itſelf
    -1.22
     myſelf
    -1.19
     pleaſure
    -1.16
     Efq
    -1.16
     Monfieur
    -1.11
     Shakspeare
    -1.11
     raiſ
    -1.10
    WriteTagHelper
    -1.10
    GEBURTSDATUM
    -1.10
    POSITIVE LOGITS
     main
    0.95
     own
    0.86
     biggest
    0.84
     entire
    0.84
    ’
    0.82
     new
    0.80
     “
    0.79
     total
    0.79
     initial
    0.79
     latest
    0.79
    Act Density 0.400%

    No Known Activations