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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and parentheses, as well as highlighting instances where choices and inclusivity are mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barth
    -0.16
    utin
    -0.15
     Seb
    -0.14
    .Sys
    -0.14
     mut
    -0.14
    AFP
    -0.14
    uiltin
    -0.14
    emoc
    -0.14
    OTH
    -0.13
    aunch
    -0.13
    POSITIVE LOGITS
    åIJ¦
    0.14
    UTE
    0.14
    eland
    0.14
    orden
    0.14
    iron
    0.13
     coincidence
    0.13
    alk
    0.13
     पश
    0.13
    defs
    0.13
    ester
    0.13
    Act Density 0.417%

    No Known Activations