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

    Neuronpedia

    INDEX
    Explanations

    words related to structure and arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comedy
    -0.23
     comedian
    -0.21
     comed
    -0.19
     comply
    -0.19
    .nz
    -0.19
     Comic
    -0.18
     compressor
    -0.18
    Comic
    -0.18
     comic
    -0.18
    Commerce
    -0.18
    POSITIVE LOGITS
    iskey
    0.16
    ible
    0.16
    aire
    0.16
    .DataAnnotations
    0.16
    pared
    0.16
    luv
    0.15
    merc
    0.15
    wealth
    0.15
    erce
    0.15
    à¹Ĥย
    0.15
    Act Density 0.138%

    No Known Activations