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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal aspirations and household dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reck
    -0.15
    ariat
    -0.14
    zek
    -0.14
     balk
    -0.14
    uffman
    -0.14
    LB
    -0.14
    ienes
    -0.13
    aths
    -0.13
    utes
    -0.13
     Dog
    -0.13
    POSITIVE LOGITS
    ocz
    0.16
    Terr
    0.15
    iple
    0.15
     Terr
    0.14
    isphere
    0.14
     acomp
    0.13
     embargo
    0.13
    gua
    0.13
    à¸Ńม
    0.13
    oka
    0.13
    Act Density 0.005%

    No Known Activations