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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and first-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first and second person pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.49
     Numerade
    -0.45
    fjspx
    -0.44
    matory
    -0.44
    檚
    -0.44
    はじめに
    -0.41
     Rank
    -0.41
     sputnik
    -0.40
    ğlık
    -0.40
    Plays
    -0.40
    POSITIVE LOGITS
     noDo
    0.52
     dovre
    0.47
     XCTest
    0.47
     chúng
    0.46
     BoxFit
    0.45
    SpringRunner
    0.45
    pingente
    0.43
     käyt
    0.42
     powin
    0.41
    /**
    0.40
    Act Density 0.152%

    No Known Activations