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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.66
     Paglinawan
    -0.61
    jsii
    -0.59
    AccessorTable
    -0.59
    клопе
    -0.56
    complexContent
    -0.56
    يكب
    -0.56
    ArrowToggle
    -0.56
    Hozzáférés
    -0.55
     kaynağından
    -0.54
    POSITIVE LOGITS
    wise
    0.69
    liest
    0.67
    WISE
    0.60
     clock
    0.58
    lier
    0.57
     crazy
    0.54
     minded
    0.52
     quoi
    0.47
     unto
    0.47
    wiſe
    0.47
    Act Density 0.108%

    No Known Activations