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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific programming-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allery
    -0.17
    ombo
    -0.16
    ibal
    -0.16
    hari
    -0.16
    éIJ
    -0.15
    ibel
    -0.15
    ometr
    -0.15
    ãĥ«ãĥī
    -0.15
    ÅŁam
    -0.15
    loven
    -0.15
    POSITIVE LOGITS
    edes
    0.17
    otes
    0.14
    873
    0.14
     Chun
    0.14
    rd
    0.14
     Ped
    0.14
     Clara
    0.14
    ze
    0.14
     Bull
    0.14
     socio
    0.13
    Act Density 0.003%

    No Known Activations