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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åłĤ
    -0.16
     Verfügung
    -0.16
    illin
    -0.15
    onical
    -0.15
    .googlecode
    -0.15
     EITHER
    -0.15
    orno
    -0.14
    either
    -0.14
    γγ
    -0.13
    ãģĺãĤĥãģªãģĦ
    -0.13
    POSITIVE LOGITS
     many
    0.37
     most
    0.32
     any
    0.30
    many
    0.29
     so
    0.28
     with
    0.23
     Many
    0.23
    Many
    0.23
     MANY
    0.22
     clock
    0.22
    Act Density 0.056%

    No Known Activations