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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "comp" or its variations, often in reference to complex topics or organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pr
    -0.19
    amoto
    -0.18
    pper
    -0.16
    prs
    -0.16
    psilon
    -0.16
    äge
    -0.15
    ppers
    -0.15
    ras
    -0.15
    ippy
    -0.15
    ialog
    -0.14
    POSITIVE LOGITS
     comp
    0.39
     Comp
    0.36
    .comp
    0.32
    -comp
    0.31
    (comp
    0.30
    Comp
    0.29
    comp
    0.27
    ensation
    0.27
     komp
    0.27
    .Comp
    0.25
    Act Density 0.009%

    No Known Activations