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

    Neuronpedia

    INDEX
    Explanations

    concepts related to technology and its applications in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycop
    -0.15
    zano
    -0.14
    (?
    -0.14
    åĿĩ
    -0.14
     Gim
    -0.14
    rl
    -0.13
    htag
    -0.13
    legg
    -0.13
    obody
    -0.13
    illance
    -0.13
    POSITIVE LOGITS
     itself
    0.22
     has
    0.22
     is
    0.21
     isn
    0.18
     can
    0.18
     seems
    0.17
    alone
    0.17
    appe
    0.16
     may
    0.16
     provides
    0.15
    Act Density 0.494%

    No Known Activations