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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or joint efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    773
    -0.14
    IGHT
    -0.14
    smarty
    -0.13
    ordial
    -0.13
    TRL
    -0.13
     blah
    -0.13
    eph
    -0.13
    bases
    -0.13
    bios
    -0.13
    nection
    -0.13
    POSITIVE LOGITS
     list
    0.28
     List
    0.22
     lista
    0.20
     dozens
    0.20
    åĪĹ表
    0.20
     numerous
    0.19
    -list
    0.19
     Numerous
    0.19
    clist
    0.19
    list
    0.18
    Act Density 0.031%

    No Known Activations