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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "imp" indicating strong influence or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUENCE
    -0.17
    erd
    -0.16
    itel
    -0.15
    eken
    -0.15
    .est
    -0.15
    xic
    -0.15
    ering
    -0.14
    .TabIndex
    -0.14
     wah
    -0.14
    ABL
    -0.14
    POSITIVE LOGITS
     Imp
    0.24
    .Imp
    0.21
     imp
    0.21
    Imp
    0.19
     IMP
    0.18
     Im
    0.18
    .imp
    0.17
    _imp
    0.17
     имп
    0.16
     Inn
    0.16
    Act Density 0.022%

    No Known Activations