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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ
    -0.15
    887
    -0.14
    asmine
    -0.14
    inerary
    -0.14
    881
    -0.14
    ijing
    -0.14
    olars
    -0.14
    noÅĽÄĩ
    -0.14
    Ùħد
    -0.14
     Hint
    -0.13
    POSITIVE LOGITS
     Barnett
    0.16
     Communities
    0.16
     sonu
    0.15
    aylight
    0.15
    licken
    0.14
    .DrawLine
    0.14
    .pb
    0.13
    bsolute
    0.13
    olut
    0.13
    .rd
    0.13
    Act Density 0.136%

    No Known Activations