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
     papel
    -0.47
    Slope
    -0.42
    chien
    -0.41
     Commencez
    -0.41
    тивной
    -0.40
     Slope
    -0.40
    ラク
    -0.39
     côtés
    -0.39
    优先
    -0.38
    stoj
    -0.38
    POSITIVE LOGITS
     tightly
    0.82
     claust
    0.81
     Restriction
    0.80
     confines
    0.79
     restrictive
    0.78
     Strict
    0.78
     Efq
    0.75
     isolation
    0.75
     restriction
    0.74
     Restrictions
    0.74
    Act Density 0.393%

    No Known Activations