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

    Neuronpedia

    INDEX
    Explanations

    references to processes or actions involving revision and reconstruction

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.88
     back
    -0.81
     vrá
    -0.76
    restore
    -0.76
     tillbaka
    -0.75
     comeback
    -0.75
     tilbake
    -0.74
    })`
    -0.73
    back
    -0.73
     returned
    -0.73
    POSITIVE LOGITS
    orld
    0.57
    AccessorTable
    0.57
     Brant
    0.53
     cast
    0.51
    philly
    0.49
    twimg
    0.48
    featureID
    0.47
     зв
    0.47
    Cast
    0.46
    rungsseite
    0.46
    Act Density 0.046%

    No Known Activations