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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating choice or comparison between options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    choice between items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Église
    -0.39
    Outro
    -0.37
     relev
    -0.37
     dAtA
    -0.36
    Kaynakça
    -0.36
     AssemblyCulture
    -0.36
     Record
    -0.36
    Funk
    -0.36
    Fim
    -0.35
     STM
    -0.35
    POSITIVE LOGITS
    inSlope
    0.59
     wyboru
    0.58
     escolha
    0.56
    RTLR
    0.53
     escoger
    0.53
     prefier
    0.52
     tercih
    0.52
    setupUi
    0.51
     either
    0.51
     createState
    0.51
    Act Density 0.017%

    No Known Activations