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

    Neuronpedia

    INDEX
    Explanations

    references to familial and close relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inar
    -0.16
    umpy
    -0.15
    yat
    -0.15
    .jasper
    -0.14
    bud
    -0.14
    buch
    -0.14
    aning
    -0.14
    wich
    -0.14
    warf
    -0.14
    finity
    -0.13
    POSITIVE LOGITS
     Nack
    0.15
    _keeper
    0.15
     Alman
    0.14
     sucker
    0.14
    ORB
    0.13
    alam
    0.13
    592
    0.13
    rž
    0.13
    /misc
    0.13
     contr
    0.13
    Act Density 0.061%

    No Known Activations