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

    Neuronpedia

    INDEX
    Explanations

    references to web domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.19
    OptionsMenu
    -0.17
    orem
    -0.15
    bundle
    -0.14
    eid
    -0.14
    burg
    -0.14
    combe
    -0.14
     Haw
    -0.14
    (s
    -0.13
    curity
    -0.13
    POSITIVE LOGITS
    .au
    0.49
    .ua
    0.32
    lify
    0.29
    .br
    0.28
    .mx
    0.25
    .cn
    0.24
    .cy
    0.23
    .bd
    0.23
    .uk
    0.22
    .lb
    0.21
    Act Density 0.047%

    No Known Activations