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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and relationship dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    openConnection
    -0.66
    contentLoaded
    -0.58
    DockStyle
    -0.56
    rawDesc
    -0.56
     AssemblyCompany
    -0.55
    ConstraintMaker
    -0.54
    /***/
    -0.54
     TAMBÉM
    -0.54
    DOCTYPE
    -0.53
    ########.
    -0.52
    POSITIVE LOGITS
     accomplished
    0.88
     accomplish
    0.80
     accomplishing
    0.67
    Accomplished
    0.65
     done
    0.65
    seamnă
    0.65
     accomp
    0.63
     SAY
    0.61
     achieved
    0.60
     learned
    0.59
    Act Density 0.225%

    No Known Activations