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

    Neuronpedia

    INDEX
    Explanations

    instances of social or casual interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uelle
    -0.19
    аÑĢÑĩ
    -0.16
    #=
    -0.15
    fts
    -0.15
     padd
    -0.14
    tember
    -0.14
    aaS
    -0.14
     Yates
    -0.14
    iode
    -0.14
    htar
    -0.14
    POSITIVE LOGITS
     fur
    0.15
    mate
    0.15
    encode
    0.15
     Fur
    0.15
    æ¬ł
    0.14
    ThreadId
    0.14
     ipt
    0.14
     Standards
    0.14
    emplate
    0.14
    ocab
    0.13
    Act Density 0.008%

    No Known Activations