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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.72
    oes
    -0.69
     Classification
    -0.66
     1932
    -0.64
    arsity
    -0.64
     2024
    -0.64
    pex
    -0.64
    oresc
    -0.63
     [|
    -0.63
    Enlarge
    -0.62
    POSITIVE LOGITS
     than
    1.11
    natureconservancy
    0.90
     stringent
    0.89
    than
    0.88
     ado
    0.87
     sophisticated
    0.85
     elaborate
    0.84
     complicated
    0.84
     importantly
    0.83
     efficient
    0.82
    Act Density 0.094%

    No Known Activations