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

    Neuronpedia

    INDEX
    Explanations

    the word "Tri" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Tri" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.97
     deed
    -0.78
     deduction
    -0.69
     IST
    -0.68
     deeds
    -0.68
    士
    -0.67
    INESS
    -0.66
     CPC
    -0.64
    ulators
    -0.63
     saline
    -0.62
    POSITIVE LOGITS
    pling
    1.10
    assic
    1.07
    umph
    0.96
    ppy
    0.95
    reme
    0.94
    pled
    0.93
    angular
    0.93
    adic
    0.91
    ples
    0.91
    ply
    0.90
    Act Density 0.012%

    No Known Activations