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

    Neuronpedia

    INDEX
    Explanations

    numeric codes or identifiers associated with scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.85
     conjunta
    -0.78
     themselves
    -0.78
     collectively
    -0.77
    Rohy
    -0.73
     Their
    -0.72
     juntos
    -0.70
     nhau
    -0.70
    Their
    -0.69
     their
    -0.69
    POSITIVE LOGITS
     solo
    0.61
     الدولى
    0.59
    Solo
    0.58
    一人で
    0.58
    WriteTagHelper
    0.58
     sozinho
    0.56
     himself
    0.56
    ItemSelected
    0.54
     single
    0.54
     själv
    0.53
    Act Density 0.261%

    No Known Activations