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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds and their structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olib
    -0.17
    loid
    -0.16
    uum
    -0.16
    agog
    -0.15
    uble
    -0.14
    hora
    -0.14
    umat
    -0.14
    enger
    -0.13
    mania
    -0.13
    ych
    -0.13
    POSITIVE LOGITS
    館
    0.17
    PFN
    0.15
     Kaplan
    0.15
    æĹħ
    0.14
    tam
    0.14
     Hein
    0.13
    837
    0.13
    ASCADE
    0.13
     substit
    0.13
     Piper
    0.13
    Act Density 0.009%

    No Known Activations