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

    Neuronpedia

    INDEX
    Explanations

    references to figures or tables in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izen
    -0.18
     MPU
    -0.15
    LOOR
    -0.15
    imen
    -0.15
    coe
    -0.15
    CHAT
    -0.15
    θο
    -0.15
    æŀľ
    -0.14
    æ¯ķ
    -0.14
    usu
    -0.14
    POSITIVE LOGITS
    سر
    0.16
    infeld
    0.15
    oub
    0.15
    orias
    0.15
    -mf
    0.15
     Kaplan
    0.14
    @js
    0.14
    usercontent
    0.13
     ori
    0.13
    cip
    0.13
    Act Density 0.040%

    No Known Activations