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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enberg
    -0.17
     Petroleum
    -0.15
     Care
    -0.14
    wyn
    -0.14
     PCA
    -0.14
    lette
    -0.14
    opo
    -0.14
    üçük
    -0.14
    oom
    -0.14
    dz
    -0.13
    POSITIVE LOGITS
     couple
    0.22
    UPLE
    0.18
     families
    0.18
     family
    0.18
     Couple
    0.17
    riv
    0.17
     couples
    0.17
    ilden
    0.15
    çī
    0.15
    family
    0.15
    Act Density 0.482%

    No Known Activations