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

    Neuronpedia

    INDEX
    Explanations

    words associated with charitable events and fundraising activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isin
    -0.15
     Workout
    -0.14
    RAND
    -0.14
    PID
    -0.14
    ultz
    -0.14
    ORT
    -0.14
     Wol
    -0.13
    àµįà´
    -0.13
    ength
    -0.13
    igu
    -0.13
    POSITIVE LOGITS
     solic
    0.25
     redund
    0.23
     redundancy
    0.21
     Solic
    0.20
     mum
    0.18
     GP
    0.18
     Thames
    0.17
     train
    0.17
     stag
    0.17
     blo
    0.17
    Act Density 0.377%

    No Known Activations