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

    Neuronpedia

    INDEX
    Explanations

    words related to choices and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.17
    zer
    -0.15
    exus
    -0.15
    newsletter
    -0.14
    oun
    -0.14
    ï¼£
    -0.14
    visor
    -0.14
    Newsletter
    -0.13
    оÑĤов
    -0.13
    quist
    -0.13
    POSITIVE LOGITS
    @js
    0.15
    405
    0.14
    .ic
    0.14
    rah
    0.14
    ocol
    0.14
     Damen
    0.14
     Perr
    0.14
    art
    0.14
     supra
    0.13
    antan
    0.13
    Act Density 0.610%

    No Known Activations