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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "our" and variations of it

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

    consecutive verbs or other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    por
    -0.37
    POR
    -0.35
    要
    -0.34
     مما
    -0.34
    EObject
    -0.34
    　　　　　　
    -0.34
    ，
    -0.34
    ','
    -0.33
     PES
    -0.33
     Chor
    -0.33
    POSITIVE LOGITS
     Theſe
    0.83
    ScopeManager
    0.77
     queſta
    0.76
    AndEndTag
    0.74
    pośred
    0.73
     faſt
    0.73
    期刊论文
    0.71
     témoig
    0.71
    styleUrls
    0.70
    ロウィン
    0.70
    Act Density 0.044%

    No Known Activations