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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective experiences or shared perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.94
     myſelf
    -0.94
    SharedDtor
    -0.91
    MigrationBuilder
    -0.90
     wireType
    -0.90
    хьтан
    -0.86
     <=",
    -0.84
    JspWriter
    -0.84
    IonicModule
    -0.83
    fjspx
    -0.83
    POSITIVE LOGITS
     ведь
    0.65
     hey
    0.64
    毕竟
    0.63
    畢竟
    0.62
     what
    0.61
     it
    0.59
    Isn
    0.59
     isn
    0.59
     aren
    0.58
     Ведь
    0.57
    Act Density 0.103%

    No Known Activations