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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enment
    -0.07
    pping
    -0.06
    aul
    -0.06
    aad
    -0.05
     ever
    -0.05
    æĻ
    -0.05
     Fernandez
    -0.05
    ç§ĭ
    -0.05
    enburg
    -0.05
     undert
    -0.05
    POSITIVE LOGITS
    _FT
    0.08
    리ìĬ¤
    0.07
    kop
    0.07
    ãĥ¼ãĥľ
    0.07
    .semantic
    0.07
    ãĥ³ãĥķ
    0.07
    ãĥ«ãĥķ
    0.07
     mieux
    0.07
     olursa
    0.07
    xlsx
    0.06
    Act Density 0.033%

    No Known Activations