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

    Neuronpedia

    INDEX
    Explanations

    references to entities or quantities, particularly focusing on the use of "one" and similar terms

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

    one followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.51
    FieldDescriptor
    -0.51
    $_['
    -0.47
    ViewInit
    -0.46
    UnusedPrivate
    -0.44
    jfree
    -0.44
    CodeAnalysis
    -0.44
    elemField
    -0.42
    AndroidJUnit
    -0.42
     useAuth
    -0.42
    POSITIVE LOGITS
     nôtre
    0.47
    them
    0.44
     invokingState
    0.43
     them
    0.42
     дописавши
    0.42
     vôtre
    0.38
     yours
    0.37
     judiciaire
    0.36
     niitä
    0.36
    它们
    0.36
    Act Density 0.570%

    No Known Activations