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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "har" in various forms, likely related to a specific subject or context

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

    Har followed by MV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pointe
    -0.59
    openzeppelin
    -0.58
     Boi
    -0.58
    onee
    -0.57
    StoryboardSegue
    -0.56
     Cleo
    -0.55
     Newt
    -0.54
     Bloc
    -0.53
    ctu
    -0.53
    vivi
    -0.52
    POSITIVE LOGITS
     Har
    0.82
    Har
    0.81
    har
    0.80
     Harrell
    0.79
    HAR
    0.75
     HAR
    0.73
     Harlow
    0.73
     Harbour
    0.70
     Harlan
    0.69
     Harwood
    0.66
    Act Density 0.009%

    No Known Activations