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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns and phrases related to self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dra
    -0.17
     itself
    -0.16
     himself
    -0.16
    nc
    -0.14
    ncy
    -0.14
    Wheel
    -0.14
    apolis
    -0.14
    ochrome
    -0.14
    enheim
    -0.14
    eming
    -0.14
    POSITIVE LOGITS
    zelf
    0.26
    elf
    0.19
    /us
    0.16
    lef
    0.16
    elves
    0.15
    'icon
    0.15
    acey
    0.15
    zel
    0.14
    IPP
    0.14
    erv
    0.14
    Act Density 0.067%

    No Known Activations