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

    Neuronpedia

    INDEX
    Explanations

    terms related to isolation and seclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascal
    -0.17
    ../../../
    -0.17
    /current
    -0.16
    ero
    -0.16
    ãģªãģĦ
    -0.15
    rik
    -0.15
    η
    -0.15
    ritis
    -0.15
    ooled
    -0.15
    ê»ĺ
    -0.15
    POSITIVE LOGITS
    /is
    0.21
    olated
    0.19
    amba
    0.19
     isol
    0.18
    away
    0.18
    anlar
    0.16
    olation
    0.16
    407
    0.15
    ively
    0.15
     isolation
    0.15
    Act Density 0.020%

    No Known Activations