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

    Neuronpedia

    INDEX
    Explanations

    expressions related to adaptation and habituation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.52
    WaitGroup
    -0.48
    MigrationBuilder
    -0.48
     PeEnEo
    -0.47
    BoxShadow
    -0.47
    setof
    -0.46
     propOrder
    -0.46
     Waray
    -0.44
    +#+#
    -0.44
    IActionResult
    -0.43
    POSITIVE LOGITS
     kebiasaan
    0.56
     costumbre
    0.54
     habit
    0.49
     привы
    0.48
     habitu
    0.47
    慣れて
    0.47
     familiarity
    0.47
    习惯
    0.47
    posedge
    0.47
     Learned
    0.46
    Act Density 0.751%

    No Known Activations