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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or structures within text

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

    colon followed by explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pingente
    -0.64
    ientras
    -0.62
     ajudá
    -0.56
    ortecedor
    -0.56
     Infór
    -0.55
    wifery
    -0.55
     kaarangay
    -0.54
    Reprodução
    -0.54
    tableFuture
    -0.54
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
    :
    0.74
    :<
    0.55
    :\
    0.53
    :</
    0.53
    :,
    0.52
    :(
    0.51
    :\\
    0.49
    】:
    0.48
    :-
    0.48
    :/
    0.46
    Act Density 0.084%

    No Known Activations