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

    Neuronpedia

    INDEX
    Explanations

    terms related to communication and agreement within a collaborative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entyfik
    -0.53
    feira
    -0.50
    licó
    -0.48
     gas
    -0.48
    uParam
    -0.47
    ấy
    -0.47
     biệt
    -0.46
     Comment
    -0.46
     ujednoznacz
    -0.46
    sene
    -0.45
    POSITIVE LOGITS
     writing
    1.87
     write
    1.83
     written
    1.70
    write
    1.69
     writes
    1.61
    writing
    1.61
     wrote
    1.59
     Writing
    1.52
    writes
    1.47
     WRITE
    1.47
    Act Density 0.433%

    No Known Activations