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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.15
    /topic
    -0.14
     Schn
    -0.14
    ίνα
    -0.14
    ằng
    -0.14
     rumored
    -0.14
    人æ°ij
    -0.14
    asm
    -0.14
    Persons
    -0.13
    iox
    -0.13
    POSITIVE LOGITS
     Speaking
    0.23
    Speaking
    0.21
     speaking
    0.19
     Mr
    0.16
    anine
    0.16
     Sir
    0.16
    ernaut
    0.16
     bosses
    0.16
    ãĤ«ãĥĨ
    0.15
    igung
    0.15
    Act Density 0.059%

    No Known Activations