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

    Neuronpedia

    INDEX
    Explanations

    references to familial and community relationships

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

    words ending in hood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sri
    -0.52
     Sri
    -0.51
     lorry
    -0.50
    Vicente
    -0.50
    \{\\
    -0.49
    Inspector
    -0.48
     inspector
    -0.47
     Inspector
    -0.47
    ([(
    -0.46
     Minister
    -0.45
    POSITIVE LOGITS
    hood
    2.16
    HOOD
    1.75
    thood
    1.48
    Hood
    1.21
     hood
    1.18
     Hood
    1.16
     womanhood
    1.00
     motherhood
    0.99
     manhood
    0.95
     Brotherhood
    0.86
    Act Density 0.005%

    No Known Activations