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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .uf
    -0.17
     stock
    -0.15
    ctr
    -0.15
    uf
    -0.15
    uth
    -0.14
     Stock
    -0.14
    stock
    -0.13
    zeug
    -0.13
    anch
    -0.13
    cker
    -0.13
    POSITIVE LOGITS
    ritten
    0.15
    olith
    0.15
    iglia
    0.15
    ivery
    0.15
     DOT
    0.14
     Psi
    0.14
     attendant
    0.14
    icontrol
    0.14
     Dai
    0.14
     вз
    0.14
    Act Density 0.052%

    No Known Activations