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

    Neuronpedia

    INDEX
    Explanations

    instances of playfulness or experimentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     înal
    -0.62
     vérit
    -0.60
    stateProvider
    -0.57
     EconPapers
    -0.56
    barui
    -0.55
     survey
    -0.55
     silenzio
    -0.54
    UnusedPrivate
    -0.54
    jante
    -0.53
     gemens
    -0.53
    POSITIVE LOGITS
     tinkering
    1.17
     experimenting
    1.03
     manipulations
    1.02
     manipulating
    1.02
     experimentation
    0.99
     manipulation
    0.98
     tinker
    0.98
     manip
    0.98
     manipulate
    0.97
     toys
    0.96
    Act Density 0.205%

    No Known Activations