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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynn
    -0.17
     Boeh
    -0.16
    ught
    -0.15
    bsolute
    -0.14
    ubar
    -0.14
    ustr
    -0.14
    WithOptions
    -0.14
    icemail
    -0.13
    *)"
    -0.13
    atalog
    -0.13
    POSITIVE LOGITS
    że
    0.15
    upp
    0.13
     Dow
    0.12
    patrick
    0.12
    lena
    0.12
     courthouse
    0.12
    icha
    0.12
     Sext
    0.12
     Terror
    0.12
    ãģ¾ãģĻ
    0.12
    Act Density 0.051%

    No Known Activations