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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reno
    -0.17
    cio
    -0.16
    ieber
    -0.16
    rane
    -0.16
    pper
    -0.15
     Pier
    -0.14
     Ones
    -0.14
    dsp
    -0.14
    NoSuch
    -0.14
    ÑĤо
    -0.13
    POSITIVE LOGITS
     odd
    0.18
    ãĤ¯ãĥ©ãĥĸ
    0.14
    izarre
    0.14
    pNet
    0.14
    arp
    0.14
     cach
    0.13
    din
    0.13
    odd
    0.13
    edic
    0.13
    Odd
    0.13
    Act Density 0.031%

    No Known Activations