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

    Neuronpedia

    INDEX
    Explanations

    instances of simultaneous actions or states involving multiple participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    951
    -0.17
    378
    -0.16
    207
    -0.14
    ensis
    -0.14
     Marble
    -0.14
    709
    -0.14
    642
    -0.14
     portion
    -0.14
    ached
    -0.14
    ober
    -0.14
    POSITIVE LOGITS
    dere
    0.19
    omon
    0.15
    vez
    0.15
    ľ´
    0.15
    ey
    0.14
    DownLatch
    0.14
    ledon
    0.14
     fart
    0.14
    ongo
    0.13
    reeze
    0.13
    Act Density 0.520%

    No Known Activations