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

    Neuronpedia

    INDEX
    Explanations

    expressions related to directing attention or indicating something specific

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CommonModule
    -0.64
     للمعارف
    -0.61
    usermodel
    -0.59
    tagHelperRunner
    -0.58
     Casanova
    -0.57
    gameserver
    -0.54
     vorbehalten
    -0.54
     encarga
    -0.54
     licencia
    -0.54
     contextLoads
    -0.53
    POSITIVE LOGITS
     pointing
    1.60
     pointed
    1.44
    pointing
    1.18
     apont
    1.16
     pointers
    1.08
    pointed
    1.05
     pointer
    0.97
     apon
    0.96
     apunt
    0.92
     указыва
    0.91
    Act Density 0.124%

    No Known Activations