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

    Neuronpedia

    INDEX
    Explanations

    references to isolation and confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBarButtonItem
    -0.32
     emlé
    -0.29
     taraf
    -0.29
     gratuit
    -0.29
     atau
    -0.29
    раз
    -0.29
     teis
    -0.28
    นะ
    -0.28
     gratuita
    -0.28
     catch
    -0.27
    POSITIVE LOGITS
     isolation
    0.96
     Isolation
    0.92
    Isolation
    0.89
    isolation
    0.89
     seclusion
    0.87
     geïsole
    0.86
     reclu
    0.76
     isolate
    0.76
     isol
    0.75
     isolated
    0.75
    Act Density 0.684%

    No Known Activations