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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating logical connections and assumptions in reasoning

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

    furthermore, moreover, in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.49
    っ
    -0.44
    herr
    -0.43
     wide
    -0.42
    yor
    -0.41
    UNT
    -0.40
     Lone
    -0.38
     either
    -0.38
    OID
    -0.38
     Yeti
    -0.38
    POSITIVE LOGITS
     dessutom
    0.66
    TagHelper
    0.61
    rungsseite
    0.59
     navíc
    0.58
    tagHelperRunner
    0.56
    Inoltre
    0.56
     ayrıca
    0.54
     AssemblyCulture
    0.52
     lisäksi
    0.52
     inoltre
    0.52
    Act Density 0.120%

    No Known Activations