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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" used as a comparison or to introduce similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åłĤ
    -0.17
    aps
    -0.15
    iman
    -0.15
    obia
    -0.15
    iah
    -0.14
    illin
    -0.14
    óg
    -0.14
    ropol
    -0.14
    either
    -0.14
    odore
    -0.14
    POSITIVE LOGITS
     many
    0.32
    many
    0.26
     any
    0.26
    许å¤ļ
    0.23
     most
    0.22
     muchos
    0.20
     MANY
    0.20
     everything
    0.20
    WISE
    0.19
    ä»»ä½ķ
    0.19
    Act Density 0.056%

    No Known Activations