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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ignore" and its variations in various contexts

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

    ignoring or overlooking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cshtml
    -0.53
     AssemblyProduct
    -0.51
    enderror
    -0.49
    ModelSerializer
    -0.49
    kháu
    -0.48
    tinyos
    -0.48
    XmlAccessorType
    -0.47
    fastjson
    -0.47
     canst
    -0.46
    GOTREF
    -0.46
    POSITIVE LOGITS
     ignores
    0.66
     ignored
    0.59
     ignore
    0.58
    NORE
    0.57
     Ignore
    0.56
    ignore
    0.54
     Ign
    0.54
     ignoring
    0.53
    Ignore
    0.49
     Ignoring
    0.49
    Act Density 0.012%

    No Known Activations