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

    Neuronpedia

    INDEX
    Explanations

    terms related to amplification or enhancing effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.17
    ild
    -0.15
    inkle
    -0.14
    orting
    -0.14
    atest
    -0.14
    .um
    -0.14
    ect
    -0.14
    ads
    -0.14
     afternoon
    -0.13
    912
    -0.13
    POSITIVE LOGITS
    &eacute
    0.15
    urgeon
    0.15
    etta
    0.14
    ishment
    0.14
    anium
    0.14
     اÙĦرÙĪ
    0.14
    477
    0.14
    δÏģα
    0.14
    rush
    0.14
     Pir
    0.14
    Act Density 0.015%

    No Known Activations