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

    Neuronpedia

    INDEX
    Explanations

    words related to construction or building processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhl
    -0.16
    arl
    -0.15
    PLICATION
    -0.15
    TINGS
    -0.15
    finger
    -0.14
    iera
    -0.14
    tings
    -0.14
    wares
    -0.14
    enda
    -0.14
    itlement
    -0.14
    POSITIVE LOGITS
    jug
    0.22
    solid
    0.20
    mens
    0.19
     trai
    0.18
    tra
    0.17
    olly
    0.17
    radi
    0.17
    ervative
    0.17
    omic
    0.17
     sider
    0.16
    Act Density 0.049%

    No Known Activations