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

    Neuronpedia

    INDEX
    Explanations

    references to personal abilities and capacities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usi
    -0.15
    aji
    -0.14
    bÄĽ
    -0.14
    isel
    -0.14
    渡
    -0.14
     cél
    -0.14
     Lots
    -0.13
    ilarity
    -0.13
    berman
    -0.13
    vangst
    -0.13
    POSITIVE LOGITS
     luxury
    0.31
     means
    0.30
    lux
    0.28
     tools
    0.25
     inclination
    0.24
    means
    0.23
     Luxury
    0.23
     necessary
    0.23
     wh
    0.22
     ability
    0.22
    Act Density 0.088%

    No Known Activations