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

    Neuronpedia

    INDEX
    Explanations

    words related to specific body parts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to communication methods and physical traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.67
    è£ħ
    -0.66
    Vision
    -0.64
    Layout
    -0.64
    Defense
    -0.62
    Focus
    -0.62
     Penet
    -0.62
     Initiative
    -0.62
     Vision
    -0.62
    DEF
    -0.61
    POSITIVE LOGITS
    eway
    0.97
    eways
    0.90
    etime
    0.90
    gin
    0.90
    wn
    0.90
    ables
    0.90
    ction
    0.87
    reon
    0.87
    cks
    0.86
    teenth
    0.85
    Act Density 0.073%

    No Known Activations