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

    Neuronpedia

    INDEX
    Explanations

    words that indicate measurement or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ôn
    -0.16
    iot
    -0.16
    PG
    -0.15
     odst
    -0.15
    çĵľ
    -0.15
     Reich
    -0.14
     CROSS
    -0.14
    uir
    -0.14
     Stick
    -0.14
     Isa
    -0.14
    POSITIVE LOGITS
     Sum
    0.17
    aghan
    0.17
    rane
    0.16
    tie
    0.16
    462
    0.15
    -sum
    0.15
     Deniz
    0.15
     Cassidy
    0.15
    _SUM
    0.14
    summary
    0.14
    Act Density 0.010%

    No Known Activations