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

    Neuronpedia

    INDEX
    Explanations

    repetitions and variations of the word "keep"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jsonwebtoken
    -0.56
    存于互联网档案馆
    -0.53
    IsPostBack
    -0.45
    iotensin
    -0.42
     Мексичка
    -0.41
     ujednoznacz
    -0.41
    tanleria
    -0.40
    argout
    -0.40
    دانشنامهٔ
    -0.40
     resourceCulture
    -0.39
    POSITIVE LOGITS
     track
    0.85
    Keep
    0.80
    keeps
    0.79
    keep
    0.76
     Keep
    0.76
    track
    0.72
     keep
    0.71
     tabs
    0.66
     keeps
    0.66
    Keeps
    0.65
    Act Density 0.062%

    No Known Activations