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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of value and appreciation in various contexts

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

    importance or worth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </tfoot>
    -0.60
     cops
    -0.48
     hell
    -0.47
     guess
    -0.45
     tup
    -0.45
     Obre
    -0.45
     Gual
    -0.45
     orchestra
    -0.44
     heck
    -0.43
     Sutton
    -0.43
    POSITIVE LOGITS
     valuing
    0.89
     valued
    0.87
    valued
    0.80
     valorar
    0.57
    valu
    0.54
     waard
    0.54
    珍惜
    0.53
     valuation
    0.53
     Valuation
    0.53
    重视
    0.52
    Act Density 0.009%

    No Known Activations