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

    Neuronpedia

    INDEX
    Explanations

    connections and processes related to physical effects and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iferay
    -0.18
    tement
    -0.15
     ÑĤи
    -0.15
    inger
    -0.14
     isolation
    -0.14
    (Spring
    -0.14
    mpr
    -0.14
    ullet
    -0.14
     Side
    -0.14
    usty
    -0.13
    POSITIVE LOGITS
     easier
    0.16
    ney
    0.15
     THEN
    0.15
     subsequently
    0.15
     ability
    0.15
     lump
    0.14
    arp
    0.14
     Vulner
    0.14
     ease
    0.14
     dá»ħ
    0.14
    Act Density 0.103%

    No Known Activations