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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variations of the word "This" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    this or that followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Външни
    -0.49
     []:
    -0.46
    Amicalement
    -0.45
    urlopen
    -0.44
    原始内容存档于
    -0.44
     dalamnya
    -0.44
    gunos
    -0.44
     będziemy
    -0.44
    Externe
    -0.43
     serão
    -0.43
    POSITIVE LOGITS
    kháu
    0.74
    ppuden
    0.47
     iconLine
    0.46
    enumii
    0.42
     صوتيه
    0.41
    InitVars
    0.40
    DebuggerStep
    0.39
    InjectAttribute
    0.39
     DIG
    0.37
    BagConstraints
    0.36
    Act Density 0.049%

    No Known Activations