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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and actions involving people interacting

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

    while clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.61
    帖最后由
    -0.56
     Infórmanos
    -0.56
    msford
    -0.56
    sidemargin
    -0.55
    Portail
    -0.54
    -0.54
     فريبيس
    -0.54
    MockMvc
    -0.52
     utafitiHapana
    -0.52
    POSITIVE LOGITS
     While
    0.57
     while
    0.56
    While
    0.54
     mentre
    0.53
     mientras
    0.52
     enquanto
    0.52
    mientras
    0.51
     sementara
    0.51
    while
    0.51
     Enquanto
    0.51
    Act Density 0.110%

    No Known Activations