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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases expressing belief or assertion

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

    that introduces a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.63
     <<<<<<<<<<<<<<
    -0.58
     AssemblyCompany
    -0.54
    complexContent
    -0.53
    tagHelperRunner
    -0.53
    IUrlHelper
    -0.52
    ApiModel
    -0.52
    RectangleBorder
    -0.51
     Dreamer
    -0.51
    Reminds
    -0.50
    POSITIVE LOGITS
     bahawa
    0.52
     jeżeli
    0.48
    eramente
    0.47
     bahwa
    0.46
     Daß
    0.44
     gdyż
    0.44
     efectivamente
    0.43
     ilustracja
    0.43
     μπο
    0.42
     poichè
    0.41
    Act Density 0.251%

    No Known Activations