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

    Neuronpedia

    INDEX
    Explanations

    references to the term "helm" in various contexts

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

    helm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APORE
    -0.68
    quelize
    -0.68
     Eura
    -0.68
     SAD
    -0.61
    ajoz
    -0.59
     Progres
    -0.58
     profan
    -0.57
    spli
    -0.57
    Kansas
    -0.57
     Apri
    -0.57
    POSITIVE LOGITS
     helm
    1.96
     Helm
    1.90
    Helm
    1.63
    helm
    1.44
     Helms
    0.98
     hel
    0.96
    hel
    0.74
     HEL
    0.73
     helmet
    0.71
     Hel
    0.69
    Act Density 0.002%

    No Known Activations