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

    Neuronpedia

    INDEX
    Explanations

    terms related to semantics and semantic frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jde
    -0.15
     Reese
    -0.15
    add
    -0.15
    odem
    -0.15
    گاÙĩ
    -0.14
    yr
    -0.14
    alo
    -0.13
    chn
    -0.13
    scratch
    -0.13
    uhan
    -0.13
    POSITIVE LOGITS
    cpt
    0.15
    inclu
    0.14
    AGO
    0.14
    twig
    0.14
     Sou
    0.13
    idden
    0.13
    -lfs
    0.13
    dq
    0.13
    antar
    0.13
    HostException
    0.13
    Act Density 0.005%

    No Known Activations