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

    Neuronpedia

    INDEX
    Explanations

    descriptions of quantities and attributes related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibs
    -0.17
    ipt
    -0.15
     éŁ
    -0.14
    imizer
    -0.14
    abbit
    -0.14
    ï¸ı
    -0.14
     NF
    -0.14
     Beng
    -0.14
     @@↵
    -0.14
    ropic
    -0.14
    POSITIVE LOGITS
    agens
    0.17
    aida
    0.16
    jo
    0.15
    asje
    0.15
    apon
    0.14
    kke
    0.14
    estr
    0.14
    abase
    0.13
    egers
    0.13
    aben
    0.13
    Act Density 0.070%

    No Known Activations