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

    Neuronpedia

    INDEX
    Explanations

    monetary values and their worth in various contexts

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

    worth followed by an amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    postsleuth
    -0.41
     refugi
    -0.38
    crity
    -0.38
     hırka
    -0.37
    makeConstraints
    -0.36
    ckså
    -0.36
     būt
    -0.36
     idéia
    -0.36
     Keuangan
    -0.36
    CppMethod
    -0.36
    POSITIVE LOGITS
     worth
    0.86
    Worth
    0.79
     WORTH
    0.77
     Worth
    0.74
    WORTH
    0.68
    worth
    0.68
     valuable
    0.57
     valeur
    0.56
    valuable
    0.53
     value
    0.52
    Act Density 0.012%

    No Known Activations