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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of links or calls to action for further reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lil
    -0.16
    евиÑĩ
    -0.15
    mc
    -0.14
    opus
    -0.14
     çī
    -0.14
    ples
    -0.13
    Mutable
    -0.13
    bia
    -0.13
    rotch
    -0.13
    unci
    -0.13
    POSITIVE LOGITS
    peq
    0.14
    yš
    0.14
    ocos
    0.14
     ÙĩÙĬ
    0.14
    evil
    0.14
    ocy
    0.14
    nP
    0.13
    çŃĭ
    0.13
    agar
    0.13
     Ferdinand
    0.13
    Act Density 0.021%

    No Known Activations