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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating connections and relationships in various contexts

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

    conjunctions and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.63
     queſta
    -0.63
     snippetHide
    -0.61
     ſtate
    -0.59
     Majefty
    -0.59
     GenerationType
    -0.59
    ſelves
    -0.59
    ſelf
    -0.58
     وتسجيلات
    -0.58
     SafeMath
    -0.57
    POSITIVE LOGITS
    enumi
    0.46
     thus
    0.39
     ello
    0.37
     endeavours
    0.37
     employ
    0.36
     meanwhile
    0.35
     cuarentena
    0.34
    RTCK
    0.34
    DataSnapshot
    0.34
    oubtedly
    0.33
    Act Density 0.034%

    No Known Activations