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

    Neuronpedia

    INDEX
    Explanations

    the word "for" used in various contexts

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

    purpose or beneficiary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.68
    featureID
    -0.68
    iſchen
    -0.57
    RenderAtEndOf
    -0.55
     OMITBAD
    -0.55
     AssemblyCulture
    -0.52
     tartalo
    -0.52
    :✨
    -0.51
    㤵
    -0.51
     autorytatywna
    -0.50
    POSITIVE LOGITS
     towards
    0.39
    APIView
    0.34
     fix
    0.34
     để
    0.34
     consecu
    0.33
     جهت
    0.33
     intermit
    0.33
     till
    0.32
     OF
    0.32
    &&&&
    0.32
    Act Density 0.047%

    No Known Activations