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

    Neuronpedia

    INDEX
    Explanations

    specific character sequences or patterns in names and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rake
    -0.81
     Fraz
    -0.78
     CLA
    -0.76
     Cohn
    -0.75
     gra
    -0.74
     Farmers
    -0.71
     Higgins
    -0.71
     feeds
    -0.70
     CRA
    -0.70
     CMS
    -0.70
    POSITIVE LOGITS
    un
    1.55
    uns
    1.33
    uni
    1.33
    UN
    1.32
    una
    1.29
    uno
    1.21
    une
    1.19
    unn
    1.17
    unt
    1.13
    unk
    1.07
    Act Density 0.048%

    No Known Activations