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

    Neuronpedia

    INDEX
    Explanations

    quantifiers that express quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lyon
    -0.18
    doctype
    -0.15
    oucher
    -0.15
    nton
    -0.14
    hrad
    -0.13
     kromÄĽ
    -0.13
    #End
    -0.13
     سÙħ
    -0.13
     '';č↵
    -0.13
    _REQUIRED
    -0.13
    POSITIVE LOGITS
     them
    0.25
     being
    0.21
     коÑĤоÑĢÑĭÑħ
    0.21
     which
    0.20
     of
    0.19
    them
    0.19
     ones
    0.19
    being
    0.19
     коÑĤоÑĢой
    0.18
     with
    0.17
    Act Density 0.052%

    No Known Activations